Nguyen Van Duy Khiem (EN)

12 Google Certificates: Full Coursera Course List

Mon, 27 Apr 2026 08:00:00 GMT

Introduction

This post compiles the complete course/module list for 12 Google Professional Certifications and Specializations on Coursera.

Update note (2026-04-27): The list is cross-checked from certificate/specialization pages on Coursera.

Quick Summary Table

| # | Program | Courses | Total hours (estimated) | |---|---|---:|---:| | 1 | Google AI Professional Certificate | 7 | 11 | | 2 | Google Data Analytics Professional Certificate | 9 | 152 | | 3 | Google AI Essentials (Specialization) | 5 | 8 | | 4 | Google Project Management Professional Certificate | 7 | 141 | | 5 | Google Cybersecurity Professional Certificate | 9 | 133 | | 6 | Google IT Support Professional Certificate | 6 | 122 | | 7 | Google Digital Marketing & E-commerce Professional Certificate | 8 | 120 | | 8 | Google UX Design Professional Certificate | 8 | 112 | | 9 | Google IT Automation with Python Professional Certificate | 7 | 134 | | 10 | Google Business Intelligence Professional Certificate | 4 | 56 | | 11 | Google Advanced Data Analytics Professional Certificate | 7 | 153 | | 12 | Google Prompting Essentials (Specialization) | 4 | 6 |

Total: 1148 study hours (estimated from the currently displayed Coursera durations).

1. Google AI Professional Certificate (7 courses)

Source: Coursera

1. AI Fundamentals (3 hours) View on Coursera

What you'll learn

Understand fundamental generative AI concepts and build a foundation for professional AI use.
Construct effective prompts using a structured framework to generate high-quality, relevant outputs for workplace tasks.
Evaluate AI-generated outputs for accuracy and bias and apply critical thinking to ensure responsible and ethical AI use.
Analyze your professional workflow to identify high-impact opportunities to collaborate with AI.

Skills you'll gain:

AI Enablement, AI powered creativity, Responsible AI, Prompt Patterns, Data Literacy, Artificial Intelligence, Data Synthesis, AI literacy, AI Personalization, LLM Application

Tools you'll learn:

AI Workflows, Google Gemini, Generative AI, Google Workspace

2. AI for Brainstorming and Planning (1 hour) View on Coursera

What you'll learn

Brainstorm project concepts by using AI as a creative partner to generate and expand on new ideas.
Evaluate and prioritize ideas by using AI to assess them against decision criteria and frameworks.
Strengthen project plans by using AI to identify potential gaps, risks, and dependencies in your timeline.
Manage project documentation by building a centralized knowledge hub to keep your plans and information organized.

Skills you'll gain:

AI Personalization, Product Automation, Artificial Intelligence, AI literacy, AI Enablement, Responsible AI, New Business Development

Tools you'll learn:

Google Gemini, Prompt Engineering, AI Workflows, Google Workspace, Generative AI

3. AI for Research and Insights (1 hour) View on Coursera

What you'll learn

Synthesize data sources using Gemini Deep Research to generate a comprehensive research report and actionable insights from multiple sources.
Construct a research hub in NotebookLM to summarize multimodal inputs and extract key themes across different sources.
Develop a custom AI expert using Gemini Gems to gain new perspectives on your work.
Evaluate AI-generated findings by verifying sources and grounding all responses in source documentation.

Skills you'll gain:

AI Personalization, Prompt Patterns, Decision Support Systems, Responsible AI, Artificial Intelligence, Ideation, AI literacy, Prompt Engineering, Generative AI Agents, AI Enablement

Tools you'll learn:

Google Workspace, Generative AI, Google Gemini, AI Workflows

4. AI for Writing and Communicating (1 hour) View on Coursera

What you'll learn

Synthesize meeting transcripts with Gemini in Google Meet to transform long discussions into clear summaries and organized to-do lists.
Refine your work by asking Gemini to provide critical feedback and prepare for high-stakes reviews.
Construct communication assets for different audiences with Gemini Canvas by applying distinct persona, style, and context constraints.
Evaluate communication strategies by simulating workplace scenarios and role-playing conversations with Gemini Live.

Skills you'll gain:

AI Enablement, Responsible AI, Persona Development, Report Writing, AI Personalization, Management Reporting, AI literacy, Artificial Intelligence, Stakeholder Analysis, Public Speaking

Tools you'll learn:

Generative AI, Google Workspace, AI Workflows, Google Gemini

5. AI for Content Creation (2 hours) View on Coursera

What you'll learn

Generate high-quality visual assets from a creative concept using Gemini's image and video generation models.
Transform generic slide decks into engaging visual presentations with Gemini in Google Slides.
Establish custom design guidelines to ensure all AI-generated content aligns with brand standards.
Critique creative assets by prompting AI to provide actionable feedback and specific improvements based on design criteria.

Skills you'll gain:

Artificial Intelligence, Multimodal Prompts, Visual Storytelling, AI Personalization, AI powered creativity, AI literacy, AI Enablement, Creative Design, Responsible AI

Tools you'll learn:

Google Gemini, Google Workspace, Generative AI, AI Workflows

6. AI for Data Analysis (1 hour) View on Coursera

What you'll learn

Identify success metrics by using AI to analyze business objectives and determine how to accurately measure project performance.
Clean and structure messy data by writing effective prompts to reformat and standardize unstructured information.
Generate spreadsheet formulas using natural language instructions with Gemini in Google Sheets.
Create data visualizations with AI to clearly communicate insights and trends.

Skills you'll gain:

Artificial Intelligence, Simulation and Simulation Software, AI Personalization, Business Analytics, Interactive Data Visualization, Data Presentation, Performance Analysis, Responsible AI

Tools you'll learn:

Generative AI, Google Workspace, AI Workflows, Google Gemini

7. AI for App Building (2 hours) View on Coursera

What you'll learn

Analyze your professional workflow to identify high-impact opportunities where a custom AI solution can solve a specific workplace challenge.
Construct a functional web application by using vibe coding techniques to translate natural language into working code.
Evaluate technical issues during app development by using AI to diagnose and debug code to ensure a stable and functional prototype.
Practice using advanced AI tools, like AI Studio, and gain confidence building more sophisticated and scalable custom solutions.

Skills you'll gain:

AI Enablement, Artificial Intelligence, Responsible AI, AI Personalization

Tools you'll learn:

Generative AI, Google Workspace, Google Gemini, AI Workflows

2. Google Data Analytics Professional Certificate (9 courses)

Source: Coursera

1. Foundations: Data, Data, Everywhere (13 hours) View on Coursera

What you'll learn

Define and explain key concepts involved in data analytics including data, data analysis, and data ecosystems.
Conduct an analytical thinking self assessment giving specific examples of the application of analytical thinking.
Discuss the role of spreadsheets, query languages, and data visualization tools in data analytics.
Describe the role of a data analyst with specific reference to jobs.

Skills you'll gain:

Data Analysis, Business Analytics, Data Cleansing, Data Sharing, Data-Driven Decision-Making, Analytical Skills, Data Visualization Software, Spreadsheet Software, Data Processing, SQL, Data Ethics, Data Collection, Analytics, Tableau Software, Data Visualization

Tools you'll learn:

Google Sheets

2. Ask Questions to Make Data-Driven Decisions (15 hours) View on Coursera

What you'll learn

Explain how the problem-solving road map applies to typical analysis scenarios.
Discuss the use of data in the decision-making process.
Demonstrate the use of spreadsheets to complete basic tasks of the data analyst including entering and organizing data.
Describe the key ideas associated with structured thinking.

Skills you'll gain:

Data Analysis, Communication Strategies, Stakeholder Communications, Quantitative Research, Analysis, Stakeholder Management, Smart Goals, Expectation Management, Problem Solving, Spreadsheet Software, Data-Driven Decision-Making, Analytical Skills, Data Entry

Tools you'll learn:

Dashboard

3. Prepare Data for Exploration (19 hours) View on Coursera

What you'll learn

Explain what factors to consider when making decisions about data collection.
Discuss the difference between biased and unbiased data.
Describe databases with references to their functions and components.
Describe best practices for organizing data.

Skills you'll gain:

Databases, Metadata Management, Data Quality, File Management, Data Ethics, Unstructured Data, Data Collection, SQL, Data Management, Data Security, Data Access

Tools you'll learn:

Google Sheets, Relational Databases

4. Process Data from Dirty to Clean (16 hours) View on Coursera

What you'll learn

Define different types of data integrity and identify risks to data integrity.
Apply basic SQL functions to clean string variables in a database.
Develop basic SQL queries for use on databases.
Describe the process of verifying data cleaning results.

Skills you'll gain:

Data Cleansing, Analytics, SQL, Sample Size Determination, Data Transformation, Data Validation, Data Integrity, Data Quality, Spreadsheet Software, Sampling (Statistics)

Tools you'll learn:

Google Sheets

5. Analyze Data to Answer Questions (26 hours) View on Coursera

What you'll learn

Discuss the importance of organizing your data before analysis by using sorts and filters.
Convert and format data.
Apply the use of functions and syntax to create SQL queries to combine data from multiple database tables.
Describe the use of functions to conduct basic calculations on data in spreadsheets.

Skills you'll gain:

SQL, Spreadsheet Software, Excel Formulas, Data Analysis, Data Integration, Pivot Tables And Charts, Data Manipulation, Analytics, Data Validation, Data Compilation, Data Transformation, User Feedback

Tools you'll learn:

None listed on Coursera.

6. Share Data Through the Art of Visualization (19 hours) View on Coursera

What you'll learn

Describe the use of data visualizations to talk about data and the results of data analysis.
Identify Tableau as a data visualization tool and understand its uses.
Explain what data driven stories are including reference to their importance and their attributes.
Explain principles and practices associated with effective presentations.

Skills you'll gain:

Data Visualization, Design Elements And Principles, Driving engagement, Web Content Accessibility Guidelines, Data Presentation, Dashboard Creation, Presentations, Data Storytelling, Data Visualization Software, Color Theory, Tableau Software, Data Analysis, Interactive Data Visualization

Tools you'll learn:

Dashboard

7. Introduction to Data Analysis Using Python (27 hours) View on Coursera

What you'll learn

Explain how Python is used by data professionals.
Explore basic Python building blocks, including syntax and semantics.
Understand loops, control statements, and string manipulation.
Use data structures to store and organize data.

Skills you'll gain:

Programming Principles, Analytical Skills, Data Manipulation, Data Structures, Analytics, Scripting, Object Oriented Programming (OOP), Data Analysis, Code Reusability, Data Cleansing

Tools you'll learn:

NumPy, Python Programming, Pandas (Python Package)

8. Google Data Analytics Capstone: Complete a Case Study (11 hours) View on Coursera

What you'll learn

Identify the key features and attributes of a completed case study.
Apply the practices and procedures associated with the data analysis process to a given set of data.
Discuss the use of case studies/portfolios when communicating with recruiters and potential employers.
Gain a competitive edge by learning AI skills from Google experts.

Skills you'll gain:

Analysis, Artificial Intelligence, Data Analysis, Analytics, Interviewing Skills, Data Visualization Software, Data Cleansing, Data Visualization, Data Processing, Web Presence, AI Enablement, Spreadsheet Software, Presentations, Case Studies, Portfolio Management, Analytical Skills

Tools you'll learn:

9. Accelerate Your Job Search with AI (6 hours) View on Coursera

What you'll learn

Uncover your skills and explore new career possibilities, with support from tools like Career Dreamer.
Keep your applications organized with Google Sheets.
Build a stand out resume and a step-by-step job search plan—with help from Gemini.
Prepare for interviews and practice responding to questions using NotebookLM and Gemini Live.

Skills you'll gain:

Prompt Engineering Tools, Interviewing Skills, Branding, Professional Development, AI literacy, Web Presence

Tools you'll learn:

Prompt Engineering, Generative AI, Google Gemini

3. Google AI Essentials (Specialization - 5 courses)

Source: Coursera

1. Introduction to AI (1 hour) View on Coursera

What you'll learn

Define the field of AI
Explain how AI functions at a basic level, including how AI technology is trained to learn from data
Describe the capabilities and limitations of AI tools
Recognize the importance of human oversight when using AI

Skills you'll gain:

Artificial Intelligence and Machine Learning (AI/ML), AI Enablement, Machine Learning, Innovation, Model Training, AI literacy, Critical Thinking

Tools you'll learn:

Generative AI

2. Maximize Productivity With AI Tools (2 hours) View on Coursera

What you'll learn

Recognize how generative AI can be used for several different workplace applications
Identify opportunities to leverage AI for increased productivity and optimized work processes
Evaluate whether generative AI is an optimal tool to apply to a specific task

Skills you'll gain:

Model Training, Business Workflow Analysis, Responsible AI, AI literacy, Complex Problem Solving, AI Enablement, Operational Efficiency, AI Integrations

Tools you'll learn:

Google Sheets, Gemini, Google Workspace, Google Gemini, Productivity Software, Generative AI

3. Discover the Art of Prompting (2 hours) View on Coursera

What you'll learn

Create prompts that provide clear and specific instructions for a variety of use cases
Describe the role of writing effective prompts in producing generative AI output
Apply specific prompting techniques, including few-shot prompting

Skills you'll gain:

Content Creation, LLM Application, Prompt Patterns, Large Language Modeling, AI literacy

Tools you'll learn:

Prompt Engineering

4. Use AI Responsibly (1 hour) View on Coursera

What you'll learn

Identify AI harms and their potential impact on users and social structures
Recognize possible privacy and security repercussions of AI use
Explain risks and biases that are inherent to modern AI and best practices for how to approach them

Skills you'll gain:

Critical Thinking, Data Security, Analysis, AI Security, AI literacy, Social Impact

Tools you'll learn:

Generative AI

5. Stay Ahead of the AI Curve (2 hours) View on Coursera

What you'll learn

Develop strategies to stay up-to-date in the emerging landscape of AI
Evaluate additional AI tools and their potential for future application in the workplace
Describe a variety of innovative ways AI has been integrated into the workplace

Skills you'll gain:

Analysis, AI Integrations, AI literacy, Strategic Thinking, AI Enablement

Tools you'll learn:

Generative AI

4. Google Project Management Professional Certificate (7 courses)

Source: Coursera

1. Foundations of Project Management (13 hours) View on Coursera

What you'll learn

Describe project management skills, roles, and responsibilities across a variety of industries.
Explain the project management life cycle and compare different program management methodologies.
Define organizational structure and organizational culture and explain how it impacts project management.

Skills you'll gain:

Project planning, program management, project coordination, strategic thinking, agile project management, organizational change, project management life cycle, waterfall methodology

Tools you'll learn:

None listed on Coursera.

2. Project Initiation: Starting a Successful Project (15 hours) View on Coursera

What you'll learn

Understand the significance of the initiation phase of the project life cycle.
Understand the key components of project charters and develop a project charter for project initiation.
Complete a stakeholder analysis and utilize RACI charts to define and communicate project team member responsibilities.
Evaluate various project management tools to meet project needs.

Skills you'll gain:

Smart goals, prompt engineering tools, business writing, scope management, strategic thinking, accountability frameworks, project management life cycle, project documentation

Tools you'll learn:

Project management software

3. Project Planning: Putting It All Together (23 hours) View on Coursera

What you'll learn

Describe the components of the project planning phase and their significance.
Identify tools and best practices to build a project plan and risk management plan.
Describe how to estimate, track, and maintain a budget.
Draft a communication plan and explain how to manage it.

Skills you'll gain:

Risk management, budgeting, procurement, project planning, cost management, communication planning, technical communication, milestones (project management), project risk management

Tools you'll learn:

None listed on Coursera.

4. Project Execution: Running the Project (26 hours) View on Coursera

What you'll learn

Implement the key quality management concepts of quality standards, quality planning, quality assurance, and quality control.
Demonstrate how to prioritize and analyze data and how to communicate a project’s data-informed story.
Discuss the stages of team development and how to manage team dynamics.
Describe the steps of the closing process and create project closing documentation.

Skills you'll gain:

Risk management, project documentation, quality assessment, project management, project management life cycle, stakeholder communications, project risk management, quality assurance

Tools you'll learn:

Project management software

5. Agile Project Management (20 hours) View on Coursera

What you'll learn

Explain the Agile project management approach and philosophy, including values and principles.
Discuss the pillars of Scrum and how they support Scrum values.
Describe the five important Scrum events and how to set up each event for a Scrum team.
Explain how to coach an Agile team and help them overcome challenges.

Skills you'll gain:

Coaching, backlogs, organizational change, product roadmaps, team management, user story, sprint planning, agile software development, agile product development, sprint retrospectives, prioritization

Tools you'll learn:

None listed on Coursera.

6. Capstone: Applying Project Management in the Real World (38 hours) View on Coursera

What you'll learn

Develop a comprehensive project charter using research and relevant documentation.
Determine quality standards and evaluate against those standards to ensure that the project is achieving the required level of quality.
Develop effective stakeholder reports by applying storytelling strategies to describe data.

Skills you'll gain:

Project planning, milestones (project management), stakeholder engagement, smart goals, AI enablement, meeting facilitation, quality assurance, project coordination, stakeholder communications

Tools you'll learn:

None listed on Coursera.

7. Accelerate Your Job Search with AI (6 hours) View on Coursera

What you'll learn

Uncover your skills and explore new career possibilities, with support from tools like Career Dreamer.
Keep your applications organized with Google Sheets.
Build a stand out resume and a step-by-step job search plan—with help from Gemini.
Prepare for interviews and practice responding to questions using NotebookLM and Gemini Live.

Skills you'll gain:

Prompt engineering tools, interviewing skills, branding, professional development, AI literacy, web presence

Tools you'll learn:

Prompt engineering, generative AI, Google Gemini

5. Google Cybersecurity Professional Certificate (9 courses)

Source: Coursera

1. Foundations of Cybersecurity (10 hours) View on Coursera

What you'll learn

Recognize core skills and knowledge needed to become a cybersecurity analyst
Explain security ethics
Identify how security attacks impact business operations
Identify common tools used by cybersecurity analysts

Skills you'll gain:

Cyber Risk, Security Controls, Cyber Attacks, Security Management, Network Analysis, Cybersecurity, Security Information and Event Management (SIEM), Network Security, Information Assurance, Data Ethics

Tools you'll learn:

None listed on Coursera.

2. Play It Safe: Manage Security Risks (9 hours) View on Coursera

What you'll learn

Identify the primary threats, risks, and vulnerabilities to business operations
Examine how organizations use security frameworks and controls to protect business operations
Define commonly used Security Information and Event Management (SIEM) tools
Use a playbook to respond to threats, risks, and vulnerabilities

Skills you'll gain:

Risk Analysis, Security Management, Business Risk Management, Risk Mitigation, Cyber Risk, Computer Security, Vulnerability Management, Auditing, Risk Management, Event Monitoring, Security Controls

Tools you'll learn:

Open Web Application Security Project (OWASP)

3. Connect and Protect: Networks and Network Security (12 hours) View on Coursera

What you'll learn

Define the types of networks and components of networks
Illustrate how data is sent and received over a network
Understand how to secure a network against intrusion tactics
Describe system hardening techniques

Skills you'll gain:

TCP/IP, Cloud Computing, Virtual Private Networks (VPN), Network Model, Cybersecurity, Network Architecture, Vulnerability Assessments, Network Protocols, General Networking, Cloud Security

Tools you'll learn:

Firewall

4. Tools of the Trade: Linux and SQL (23 hours) View on Coursera

What you'll learn

Explain the relationship between operating systems, applications, and hardware
Compare a graphical user interface to a command line interface
Navigate and manage the file system using Linux commands via the Bash shell
Use SQL to retrieve information from a database

Skills you'll gain:

User Accounts, File Systems, Authorization (Computing), SQL, Computer Systems, File Management, Linux Administration, Authentications, Linux Commands

Tools you'll learn:

Operating Systems, Linux, Query Languages, Bash (Scripting Language), Unix Shell, Command-Line Interface, Relational Databases

5. Assets, Threats, and Vulnerabilities (19 hours) View on Coursera

What you'll learn

Classify assets
Analyze an attack surface to find risks and vulnerabilities
Identify threats, such as social engineering, malware and web-based exploits
Summarize the threat modeling process

Skills you'll gain:

Vulnerability Management, Threat Modeling, Risk Management Framework, Cyber Risk, Cybersecurity, Identity and Access Management, Authentications, Vulnerability Assessments, Threat Detection

Tools you'll learn:

MITRE ATT&CK Framework

6. Sound the Alarm: Detection and Response (18 hours) View on Coursera

What you'll learn

Identify the steps to contain, eradicate, and recover from an incident
Analyze packets to interpret network communications
Understand basic syntax, components of signatures and logs in Intrusion Detection Systems (IDS) and Network Intrusion Detection Systems (NIDS) tools
Perform queries in Security Information and Event Management (SIEM) tools to investigate an event

Skills you'll gain:

Endpoint Detection and Response, Continuous Monitoring, Incident Management, Incident Response, Threat Detection, Event Monitoring, Network Analysis, Network Monitoring

Tools you'll learn:

Query Languages, Splunk

7. Automate Cybersecurity Tasks with Python (25 hours) View on Coursera

What you'll learn

Explain how the Python programming language is used in cybersecurity
Create new, user-defined Python functions
Use regular expressions to extract information from text
Practice debugging code

Skills you'll gain:

Scripting, Computer Programming, Algorithms, Data Structures, File I/O, Debugging, Cybersecurity, Maintainability, Programming Principles, Automation, Data Import/Export, IT Automation

Tools you'll learn:

Python Programming

8. Put It to Work: Prepare for Cybersecurity Jobs (11 hours) View on Coursera

What you'll learn

Determine when and how to escalate a security incident
Engage with the cybersecurity community
Apply for cybersecurity jobs and prepare for interviews
Gain a competitive edge by learning AI skills from Google experts

Skills you'll gain:

Data Security, Incident Response, Cybersecurity, Incident Management, Artificial Intelligence, Technical Communication, Computer Security Incident Management, Cyber Threat Intelligence

Tools you'll learn:

AI Workflows, Generative AI

9. Accelerate Your Job Search with AI (6 hours) View on Coursera

What you'll learn

Uncover your skills and explore new career possibilities, with support from tools like Career Dreamer
Keep your applications organized with Google Sheets
Build a stand out resume and a step-by-step job search plan—with help from Gemini
Prepare for interviews and practice responding to questions using NotebookLM and Gemini Live

Skills you'll gain:

Prompt Engineering Tools, Interviewing Skills, Branding, Professional Development, AI literacy, Web Presence

Tools you'll learn:

Prompt Engineering, Generative AI, Google Gemini

6. Google IT Support Professional Certificate (6 courses)

Source: Coursera

1. Technical Support Fundamentals (19 hours) View on Coursera

What you'll learn

Understand how the binary system works.
Assemble a computer from scratch.
Choose and install an operating system on a computer.
Understand what the Internet is, how it works, and the impact it has in the modern world.
Learn how applications are created and how they work under the hood of a computer.
Utilize common problem-solving methodologies and soft skills in an Information Technology setting.

Skills you'll gain:

Information Technology, System Support, Package and Software Management, Hardware Troubleshooting, Customer Support, General Networking, Computer Hardware, Software Documentation, Desktop Support

Tools you'll learn:

Linux

2. The Bits and Bytes of Computer Networking (22 hours) View on Coursera

What you'll learn

Describe computer networks in terms of a five-layer model.
Understand all of the standard protocols involved with TCP/IP communications.
Grasp powerful network troubleshooting tools and techniques.
Learn network services like DNS and DHCP that help make computer networks run.
Understand cloud computing, everything as a service, and cloud storage.

Skills you'll gain:

Network Protocols, Network Troubleshooting, Data Integrity, Network Security, Network Routing, Network Administration, Computer Networking, Virtual Private Networks (VPN), Routing Protocols, Network Routers, Network Infrastructure, Wireless Networks, Network Model, TCP/IP, Networking Hardware, General Networking

Tools you'll learn:

OSI Models, Dynamic Host Configuration Protocol (DHCP)

3. Operating Systems and You: Becoming a Power User (28 hours) View on Coursera

What you'll learn

Navigate the Windows and Linux filesystems using a graphical user interface and command line interpreter.
Set up users, groups, and permissions for account access.
Install, configure, and remove software on the Windows and Linux operating systems.
Configure disk partitions and filesystems.
Understand how system processes work and how to manage them.
Work with system logs and remote connection tools.
Utilize operating system knowledge to troubleshoot common issues in an IT Support role.

Skills you'll gain:

File Management, Desktop Support, User Accounts, Package and Software Management, OS Process Management, Operating System Administration, Linux Commands, User Provisioning, Linux Administration, Software Installation, Remote Access Systems, Technical Support and Services, System Monitoring, System Support, File Systems, Systems Administration

Tools you'll learn:

Operating Systems, Microsoft Windows, Command-Line Interface, Linux

4. System Administration and IT Infrastructure Services (24 hours) View on Coursera

What you'll learn

Utilize best practices for choosing hardware, vendors, and services for your organization.
Understand how the most common infrastructure services that keep an organization running work, and how to manage infrastructure servers.
Utilize industry tools to manage computers, user information, and user productivity.
Identify how to recover your organization's IT infrastructure in the event of a disaster.

Skills you'll gain:

Data Maintenance, Data Storage, Network Infrastructure, Servers, Lightweight Directory Access Protocols, Server Administration, Network Administration, System Configuration, Infrastructure Architecture, Technical Consulting, Cloud Computing, IT Infrastructure, Disaster Recovery, Cloud Infrastructure, Cloud Services, Cloud Management, Systems Administration, Information Technology

Tools you'll learn:

Active Directory

5. IT Security: Defense against the digital dark arts (23 hours) View on Coursera

What you'll learn

Understand how various encryption algorithms and techniques work as well as their benefits and limitations.
Understand various authentication systems and types.
Understand the difference between authentication and authorization.
Evaluate potential risks and recommend ways to reduce risk.
Recommend ways to secure a network.
Help others to understand cybersecurity concepts and methodologies.
Troubleshoot common security issues with an end-to-end understanding.

Skills you'll gain:

IT Security Architecture, Cybersecurity, Network Security, Authorization (Computing), Information Systems Security, Hardening, Computer Security Awareness Training, Threat Management, Authentications, Cryptographic Protocols, Cryptography, Malware Protection, Encryption, Security Awareness, Security Strategy, Threat Detection, Security Controls, Identity and Access Management, AI Security

Tools you'll learn:

Firewall

6. Accelerate Your Job Search with AI (6 hours) View on Coursera

What you'll learn

Uncover your skills and explore new career possibilities, with support from tools like Career Dreamer.
Build a stand out resume and a step-by-step job search plan—with help from Gemini.
Keep your applications organized with Google Sheets.
Prepare for interviews and practice responding to questions using NotebookLM and Gemini Live.

Skills you'll gain:

Prompt Engineering Tools, Interviewing Skills, Branding, Professional Development, AI literacy, Web Presence

Tools you'll learn:

Prompt Engineering, Generative AI, Google Gemini

7. Google Digital Marketing & E-commerce Professional Certificate (8 courses)

Source: Coursera

1. Foundations of Digital Marketing and E-commerce (12 hours) View on Coursera

What you'll learn

Define the fields of digital marketing and e-commerce
Describe the job responsibilities of an entry-level digital marketer and e-commerce specialist
Explain the concept of a marketing funnel
Understand the elements and goals of a digital marketing and e-commerce strategy

Skills you'll gain:

Marketing Planning, Digital Media Strategy, Marketing Strategies, Performance Metric, Customer Engagement, Brand Awareness, Search Engine Optimization, Branding, Digital Marketing, Web Analytics and SEO, Data-Driven Decision-Making, Marketing Analytics, E-Commerce, Performance marketing, Data Storytelling, Performance Measurement, Email Marketing, Conversion Funnel Analysis, Marketing, Search Engine Marketing

Tools you'll learn:

None listed on Coursera.

2. Attract and Engage Customers with Digital Marketing (14 hours) View on Coursera

What you'll learn

Recognize strategies to build brand awareness among potential customers
Explain the purpose of SEO (search engine optimization) and essential SEO terms
Optimize website content for SEO
Understand search engine marketing (SEM) and how it benefits businesses

Skills you'll gain:

Customer Analysis, Target Audience, Marketing Strategies, Search Engine Optimization, Persona Development, Marketing Strategy and Techniques, Conversion Funnel Analysis, Digital Advertising, Online Advertising, Customer Engagement, Keyword Research, Advertising Campaigns, Search Engine Marketing, Content Optimization, Digital Marketing

Tools you'll learn:

Google Ads

3. From Likes to Leads: Interact with Customers Online (21 hours) View on Coursera

What you'll learn

Define social media marketing and describe its purpose
Identify core pillars of social media marketing: strategy, planning and publishing, listening and engagement, analytics and reporting, advertising
Define the goals of a social media campaign
Write, design, and repurpose engaging content for social media

Skills you'll gain:

Content Scheduling, Marketing Analytics, Paid media, Content Creation, Social Media Management, Digital Advertising, Drive Engagement, Content Performance Analysis, Social Media Strategy, Advertising, Social Media Marketing, Branding, Social Media Campaigns, Customer Engagement, Driving engagement, Brand Awareness, Advertising Campaigns, Social Media Content, Digital Media Strategy, Brand Management

Tools you'll learn:

None listed on Coursera.

4. Think Outside the Inbox: Email Marketing (19 hours) View on Coursera

What you'll learn

Understand how email marketing fits into a digital marketing strategy
Write effective email copy, subject lines, and preview text
Test, execute, and optimize an email marketing campaign
Measure and analyze email campaign results

Skills you'll gain:

Data Ethics, Email Automation, Campaign Planning, Promotional Strategies, Email Marketing, Copywriting, Marketing Strategy and Techniques, Marketing Automation, Personally Identifiable Information, Campaign Management, Key Performance Indicators (KPIs), Digital Marketing, Digital Marketing Campaigns, Marketing Analytics, Information Privacy, Smart Goals, Goal Setting, Customer Retention

Tools you'll learn:

Digital Marketing Tools, HubSpot CRM

5. Assess for Success: Marketing Analytics and Measurement (18 hours) View on Coursera

What you'll learn

Define media planning and strategies
Describe what defines a successful marketing campaign
Evaluate metrics against performance goals and make adjustments to a marketing budget or strategy
Create presentations and reports to update stakeholders on the progress or success of a marketing campaign and important insights

Skills you'll gain:

Campaign Management, Marketing Effectiveness, Media Planning, Spreadsheet Software, Data Presentation, Paid media, Marketing Budgets, Pivot Tables And Charts, Marketing Planning, Data Visualization, Data-Driven Marketing, Key Performance Indicators (KPIs), Performance Measurement, Digital Marketing, A/B Testing, Return On Investment, Digital Marketing Campaigns, Marketing Analytics

Tools you'll learn:

Google Analytics, Google Ads

6. Make the Sale: Build, Launch, and Manage E-commerce Stores (15 hours) View on Coursera

What you'll learn

Understand essential e-commerce strategies and practices
Explain what e-commerce stores and platforms are and how they work
Create an engaging customer experience online using best practices
Set up a mock e-commerce store using Shopify

Skills you'll gain:

Retail Store Operations, Order Delivery, Online Advertising, Campaign Management, Marketing, Digital Advertising, Advertising Campaigns, Marketing Strategies, Order Fulfillment, Market Trend, Sales, Shipping and Receiving, General Sales Practices, Order Processing, Order Management, Customer experience improvement, Retail Management, Market Research, E-Commerce

Tools you'll learn:

Google Ads

7. Satisfaction Guaranteed: Develop Customer Loyalty Online (15 hours) View on Coursera

What you'll learn

Identify common strategies for building customer loyalty in e-commerce.
Successfully manage client relationships and measure satisfaction.
Gain a competitive edge by learning AI skills from Google experts.
Put together a portfolio and/or resume to present to employers.

Skills you'll gain:

Presentations, Performance Analysis, Loyalty Programs, Client Services, Digital Marketing, Customer Relationship Building, Conversion Funnel Analysis, Customer Insights, Brand Loyalty, Web Analytics, Customer Relationship Management, Customer Retention, E-Commerce, Customer Analysis, Product Improvement, Digital Analysis, Relationship Management, Customer Service, Customer Engagement

Tools you'll learn:

Digital Marketing Tools

8. Accelerate Your Job Search with AI (6 hours) View on Coursera

What you'll learn

Uncover your skills and explore new career possibilities, with support from tools like Career Dreamer.
Keep your applications organized with Google Sheets.
Build a stand out resume and a step-by-step job search plan—with help from Gemini.
Prepare for interviews and practice responding to questions using NotebookLM and Gemini Live.

Skills you'll gain:

Prompt Engineering Tools, Interviewing Skills, Branding, Professional Development, AI literacy, Web Presence

Tools you'll learn:

Prompt Engineering, Generative AI, Google Gemini

8. Google UX Design Professional Certificate (8 courses)

Source: Coursera

1. Foundations of User Experience (UX) Design (12 hours) View on Coursera

What you'll learn

Identify common job responsibilities of entry-level UX designers and other teams you might work with.
Understand foundational concepts in UX design, such as user-centered design, the design process, accessibility, and equity-focused design.
Explain why design sprints are an important and useful part of a UX designer’s work.

Skills you'll gain:

Prototyping, Design Thinking, UI/UX Research, User Research, User Centered Design, User Experience Design, Ideation, User Experience, Sprint Planning, Sprint Retrospectives, Usability, Wireframing

Tools you'll learn:

None listed on Coursera.

2. Start the UX Design Process: Empathize, Define, and Ideate (20 hours) View on Coursera

What you'll learn

Empathize with users to understand their needs and pain points.
Develop problem statements to define user needs.
Generate ideas for possible solutions to user problems.

Skills you'll gain:

Competitive Analysis, Human Centered Design, Persona Development, Ideation, Web Content Accessibility Guidelines, User Research, Human Factors, User Centered Design, Solution Design, Persona (User Experience), User Story, Design Thinking, User Experience, UI/UX Research, User Experience Design

Tools you'll learn:

None listed on Coursera.

3. Build Wireframes and Low-Fidelity Prototypes (12 hours) View on Coursera

What you'll learn

Create storyboards to come up with ideas about solutions to user needs.
Create wireframes on paper and digitally in the design tool Figma.
Build paper prototypes to create interactive designs.
Design low-fidelity prototypes in Figma.

Skills you'll gain:

User Interface and User Experience (UI/UX) Design, Interactive Design, User Interface (UI), User Research, Storyboarding, User Story, Design Elements And Principles, Wireframing, User Experience, Persona (User Experience), Prototyping, User Experience Design, Information Architecture

Tools you'll learn:

Figma (Design Software)

4. Conduct UX Research and Test Early Concepts (15 hours) View on Coursera

What you'll learn

Plan and conduct moderated and unmoderated usability studies.
Synthesize observations from usability studies and come up with insights.
Share research methodology and insights using persuasive presentation skills.
Modify low-fidelity designs based on research insights.

Skills you'll gain:

User Experience, Wireframing, Usability Testing, Prototyping, User Interface and User Experience (UI/UX) Design, User Experience Design, Information Privacy, Presentations, User Research, Data Ethics, UI/UX Research, Design Research, Research Design, Usability

Tools you'll learn:

None listed on Coursera.

5. Create High-Fidelity Designs and Prototypes in Figma (19 hours) View on Coursera

What you'll learn

Build mockups and high-fidelity prototypes in the design tool Figma.
Define and apply common visual design elements and principles.
Demonstrate how design systems can be used to organize, standardize, and enhance designs.
Understand the role of design critique sessions and feedback while iterating on designs.

Skills you'll gain:

Animations, Interaction Design, User Experience, Design Research, Design Reviews, Motion Graphics, Graphic and Visual Design, User Interface (UI) Design, Color Theory, Typography, User Experience Design, Mockups, Interactive Design, Prototyping, Design Elements And Principles, Usability Testing, Technical Communication, Usability, User Interface and User Experience (UI/UX) Design

Tools you'll learn:

Figma (Design Software)

6. Build Dynamic User Interfaces (UI) for Websites (15 hours) View on Coursera

What you'll learn

Apply each step of the UX design thinking framework (empathize, define, ideate, prototype, test) to create a dynamic website.
Plan information architecture and sitemaps for website designs.
Apply common layouts for web pages.
Complete a design project and include it in your professional UX portfolio.

Skills you'll gain:

User Experience, Mockups, Layout Design, Usability Testing, Software Design Documents, User Centered Design, Design Research, Responsive Web Design, Information Architecture, Design Reviews, Prototyping, Wireframing, Web Design, User Research, User Interface and User Experience (UI/UX) Design, User Interface (UI) Design, User Experience Design

Tools you'll learn:

Figma (Design Software)

7. Design a User Experience for Social Good & Prepare for Jobs (13 hours) View on Coursera

What you'll learn

Apply each step of the UX design thinking framework (empathize, define, ideate, prototype, test) to create a project focused on social good.
Build wireframes, mockups, and low-fidelity and high-fidelity prototypes for a dedicated mobile app and a responsive website.
Prepare to successfully interview for an entry-level UX design job.
Gain a competitive edge by learning AI skills from Google experts

Skills you'll gain:

UI/UX Research, Experience Design, Human Centered Design, User Experience Design, Usability, Responsive Web Design, Usability Testing, Design Strategies, Web Design, Ideation, Prototyping, Cross Platform Development, User Experience, User Interface and User Experience (UI/UX) Design, User Centered Design, Web Presence, Design Research, Design Thinking

Tools you'll learn:

Generative AI

8. Accelerate Your Job Search with AI (6 hours) View on Coursera

What you'll learn

Uncover your skills and explore new career possibilities, with support from tools like Career Dreamer.
Keep your applications organized with Google Sheets.
Build a stand out resume and a step-by-step job search plan—with help from Gemini.
Prepare for interviews and practice responding to questions using NotebookLM and Gemini Live.

Skills you'll gain:

Prompt Engineering Tools, Interviewing Skills, Branding, Professional Development, AI literacy, Web Presence

Tools you'll learn:

Prompt Engineering, Generative AI, Google Gemini

9. Google Advanced Data Analytics Professional Certificate (7 courses)

Source: Coursera

1. Foundations of Data Science (20 hours) View on Coursera

What you'll learn

Understand common careers and industries that use advanced data analytics.
Investigate the impact data analysis can have on decision-making.
Explain how data professionals preserve data privacy and ethics.
Develop a project plan considering roles and responsibilities of team members.

Skills you'll gain:

Machine Learning, Data-Driven Decision-Making, Business Solutions, Workflow Management, Analytics, Communication, Stakeholder Communications, Advanced Analytics, Technical Communication, Process Design, Data Science, Project Management, Analytical Skills, Data Storytelling, Data Ethics, Data Analysis

Tools you'll learn:

None listed on Coursera.

2. Go Beyond the Numbers: Translate Data into Insights (28 hours) View on Coursera

What you'll learn

Apply the exploratory data analysis (EDA) process.
Explore the benefits of structuring and cleaning data.
Investigate raw data using Python.
Create data visualizations using Tableau.

Skills you'll gain:

Data Transformation, Data Validation, Tableau Software, Data Wrangling, Data Presentation, Data Manipulation, Data Quality, Data Visualization, Exploratory Data Analysis, Data Science, Data Preprocessing, Data Analysis Software, Data Cleansing, Data Visualization Software, Data Storytelling, Data Ethics, Analysis, Technical Communication, Data Analysis

Tools you'll learn:

Python Programming

3. The Power of Statistics (31 hours) View on Coursera

What you'll learn

Explore and summarize a dataset.
Use probability distributions to model data.
Conduct a hypothesis test to identify insights about data.
Perform statistical analyses using Python.

Skills you'll gain:

Analytics, Statistical Analysis, Statistics, Statistical Programming, Statistical Inference, Data Analysis, Advanced Analytics, Statistical Methods, Probability & Statistics, Probability Distribution, Data Science, Sampling (Statistics), Statistical Hypothesis Testing, Probability, Descriptive Statistics, A/B Testing

Tools you'll learn:

Python Programming, Statistical Software

4. Regression Analysis: Simplify Complex Data Relationships (28 hours) View on Coursera

What you'll learn

Investigate relationships in datasets.
Identify regression model assumptions.
Perform linear and logistic regression using Python.
Practice model evaluation and interpretation.

Skills you'll gain:

Predictive Modeling, Variance Analysis, Regression Analysis, Statistical Methods, Machine Learning, Model Evaluation, Logistic Regression, Statistical Analysis, Statistical Modeling, Statistical Hypothesis Testing, Predictive Analytics, Correlation Analysis, Supervised Learning

Tools you'll learn:

Python Programming

5. The Nuts and Bolts of Machine Learning (34 hours) View on Coursera

What you'll learn

Identify characteristics of the different types of machine learning.
Prepare data for machine learning models.
Build and evaluate supervised and unsupervised learning models using Python.
Demonstrate proper model and metric selection for a machine learning algorithm.

Skills you'll gain:

Machine Learning Algorithms, Decision Tree Learning, Model Training, Model Evaluation, Performance Tuning, Advanced Analytics, Supervised Learning, Statistical Machine Learning, Unsupervised Learning, Random Forest Algorithm, Applied Machine Learning, Predictive Modeling, Model Optimization, Feature Engineering, Analytics, Machine Learning

Tools you'll learn:

Classification Algorithms, Python Programming

6. Google Advanced Data Analytics Capstone (6 hours) View on Coursera

What you'll learn

Examine data to identify patterns and trends.
Build models using machine learning techniques.
Create data visualizations.
Explore career resources.

Skills you'll gain:

Data Presentation, Data Analysis, Portfolio Management, Data Science, Machine Learning Methods, AI literacy, Artificial Intelligence, Applied Machine Learning, Data Visualization, Advanced Analytics, Statistical Modeling, Machine Learning, Analytical Skills, Regression Analysis, Statistical Analysis

Tools you'll learn:

Python Programming

7. Accelerate Your Job Search with AI (6 hours) View on Coursera

What you'll learn

Uncover your skills and explore new career possibilities, with support from tools like Career Dreamer.
Keep your applications organized with Google Sheets.
Build a stand out resume and a step-by-step job search plan—with help from Gemini.
Prepare for interviews and practice responding to questions using NotebookLM and Gemini Live.

Skills you'll gain:

Prompt Engineering Tools, Interviewing Skills, Branding, Professional Development, AI literacy, Web Presence

Tools you'll learn:

Prompt Engineering, Generative AI, Google Gemini

10. Google IT Automation with Python Professional Certificate (7 courses)

Source: Coursera

1. Crash Course on Python (21 hours) View on Coursera

What you'll learn

Understand what Python is and why Python is relevant to automation
Write short Python scripts to perform automated actions
Understand how to use the basic Python structures: strings, lists, and dictionaries
Create your own Python objects

Skills you'll gain:

Computational Thinking, Data Structures, Scripting Languages, Scripting, Data Store, Computer Programming Tools, Program Development, Computer Programming, Development Environment, Programming Principles, Debugging

Tools you'll learn:

Integrated Development Environments, Python Programming

2. Using Python to Interact with the Operating System (33 hours) View on Coursera

What you'll learn

Setup, configure, and use your own developer environment in Python
Manipulate files and processes running on the Operating System using Python
Understand and use regular expressions (regex), a powerful tool for processing text files
Know when to choose Bash or Python, and create small scripts using Bash

Skills you'll gain:

Development Testing, Scripting, Unit Testing, Scripting Languages, File Management, Development Environment, File I/O, Test Driven Development (TDD), Test Script Development, Test Automation, OS Process Management, Linux Commands, Software Testing

Tools you'll learn:

Unix Commands, Linux, Bash (Scripting Language), Unix Shell, Command-Line Interface, Shell Script, Operating Systems

3. Introduction to Git and GitHub (20 hours) View on Coursera

What you'll learn

Understand why version control is a fundamental tool for coding and collaboration
Install and run Git on your local machine
Use and interact with GitHub
Collaborate with others through remote repositories

Skills you'll gain:

Software Configuration Management, Version Control, Software Installation, Issue Tracking, CI/CD, Continuous Integration, Software Versioning, Code Review

Tools you'll learn:

Command-Line Interface, GitHub, Git (Version Control System), Collaborative Software

4. Troubleshooting and Debugging Techniques (19 hours) View on Coursera

What you'll learn

Analyze real-world IT problems and implement the appropriate strategies to solve those problems
Demonstrate techniques to quickly find and solve the root cause of problems in IT infrastructure
Understand the root cause for problems related to speed, crashes, or exhausted resources in your computer
Identify the most common pitfalls of your code and how to fix them

Skills you'll gain:

Continuous Integration, Problem Management, Debugging, Technical Communication, Technical Documentation, System Monitoring, Performance Tuning, Memory Management, Incident Management, Capacity Management, Continuous Monitoring, Network Troubleshooting

Tools you'll learn:

None listed on Coursera.

5. Configuration Management and the Cloud (18 hours) View on Coursera

What you'll learn

Understand the benefits of configuration management and infrastructure as code
Manage a fleet of computers using Puppet
Automatically deploy new virtual machines running in the Cloud
Deploy changes in a safe manner following CICD principles

Skills you'll gain:

Cloud Infrastructure, Cloud Management, Disaster Recovery, Cloud Services, IT Automation, Infrastructure as Code (IaC), Incident Response, Configuration Management, Continuous Monitoring, Cloud Computing, Software As A Service, Cloud Deployment, Incident Management, System Monitoring, Change Control

Tools you'll learn:

Cloud Storage, Infrastructure As A Service (IaaS), Puppet (Configuration Management Tool), Virtual Machines, Terraform

6. Automating Real-World Tasks with Python (17 hours) View on Coursera

What you'll learn

Use Python external libraries to create and modify documents, images, and messages
Understand and use Application Programming Interfaces (APIs) to interact with web services
Understand and use data serialization to send messages between running programs
Build a solution using the skills you have learned

Skills you'll gain:

Scripting, IT Automation, System Monitoring, Web Services, Email Automation, Automation

Tools you'll learn:

Application Programming Interface (API), Restful API, JSON, Python Programming

7. Accelerate Your Job Search with AI (6 hours) View on Coursera

What you'll learn

Uncover your skills and explore new career possibilities, with support from tools like Career Dreamer.
Keep your applications organized with Google Sheets.
Build a stand out resume and a step-by-step job search plan—with help from Gemini.
Prepare for interviews and practice responding to questions using NotebookLM and Gemini Live.

Skills you'll gain:

Prompt Engineering Tools, Interviewing Skills, Branding, Professional Development, AI literacy, Web Presence

Tools you'll learn:

Prompt Engineering, Generative AI, Google Gemini

11. Google Prompting Essentials (Specialization - 4 courses)

Source: Coursera

1. Start Writing Prompts like a Pro (2 hours) View on Coursera

What you'll learn

Define prompting in reference to generative AI tools.
Recognize and apply the prompting framework (task, context, references, evaluate, iterate) to create effective prompts.
Understand the importance of evaluating outputs and refining prompts as key to receiving the outputs you want.

Skills you'll gain:

AI literacy, Prompt Patterns, Prompt Engineering Tools, Context Engineering, Responsible AI, Multimodal Prompts

Tools you'll learn:

Prompt Engineering

2. Design Prompts for Everyday Work Tasks (1 hour) View on Coursera

What you'll learn

Apply the prompting framework to draft text content, help with brainstorming, create tables and timelines, and summarize lengthy text.
Apply prompting strategies to adjust the particular tone and style of text output.
Understand the benefits of long context windows.

Skills you'll gain:

AI Enablement, AI literacy, Concision, Brainstorming, LLM Application, Taking Meeting Minutes, Business Writing, AI powered creativity, Email Automation, Context Engineering, Ideation, Timelines

Tools you'll learn:

Prompt Engineering

3. Speed Up Data Analysis and Presentation Building (1 hour) View on Coursera

What you'll learn

Apply the prompting framework to extract insights from data, identify and fix spreadsheet formulas, and explore data visualization.
Develop a responsible prompting practice when entering data into generative AI tools.
Understand AI sampling parameters, how they work, and strategies for their use.

Skills you'll gain:

Spreadsheet Software, Data Analysis, Data Visualization, Data Presentation, Responsible AI, Graphing, Prompt Patterns

Tools you'll learn:

Prompt Engineering

4. Use AI as a Creative or Expert Partner (2 hours) View on Coursera

What you'll learn

Understand and apply prompt chaining, including chain of thought prompting, for complex tasks.
Understand prompt versioning and the benefits of saving and reusing your prompts over time.

Skills you'll gain:

Software Versioning, Generative AI Agents, Solution Design, Prompt Patterns, LLM Application, Multimodal Prompts, AI Personalization, AI powered creativity, Ideation, Scenario Testing

Tools you'll learn:

Agentic Workflows, Prompt Engineering

12. Google Business Intelligence Professional Certificate (4 courses)

Source: Coursera

1. Foundations of Business Intelligence (15 hours) View on Coursera

What you'll learn

Understand common careers and industries that use BI.
Investigate the impact data can have on business decision-making.
Explain the important role that BI professionals have in businesses.
Develop a BI project plan.

Skills you'll gain:

Project Implementation, Business Process, Data Pipelines, Real Time Data, Business Intelligence Software, Continuous Monitoring, Project Design, Stakeholder Communications, Plan Execution

Tools you'll learn:

Dashboard

2. The Path to Insights: Data Models and Pipelines (17 hours) View on Coursera

What you'll learn

Build data models that answer business questions.
Apply the ETL process to workplace scenarios.
Explore ETL tools.
Construct a pipeline to deliver necessary data.

Skills you'll gain:

Business Process, Data Transformation, Data Modeling, Data Integrity, Extract, Transform, Load, Data Warehousing, Databases, Performance Testing, Data Integration, Data Pipelines, Data Mart

Tools you'll learn:

Database Systems

3. Decisions, Decisions: Dashboards and Reports (18 hours) View on Coursera

What you'll learn

Design BI visualizations.
Practice using BI reporting and dashboard tools.
Create presentations to share key BI insights with stakeholders.
Develop professional materials for your job search.

Skills you'll gain:

Dashboard Creation, Tableau Software, Data Visualization Software, Performance Tuning, Performance Analysis, Interactive Data Visualization, Business Intelligence, Presentations

Tools you'll learn:

Dashboard

4. Accelerate Your Job Search with AI (6 hours) View on Coursera

What you'll learn

Uncover your skills and explore new career possibilities, with support from tools like Career Dreamer.
Keep your applications organized with Google Sheets.
Build a stand out resume and a step-by-step job search plan—with help from Gemini.
Prepare for interviews and practice responding to questions using NotebookLM and Gemini Live.

Skills you'll gain:

Prompt Engineering Tools, Interviewing Skills, Branding, Professional Development, AI literacy, Web Presence

Tools you'll learn:

Prompt Engineering, Generative AI, Google Gemini

Suggested Next Use

Use total hours to estimate a weekly learning plan.
Prioritize pathways with capstone and job-search modules if you are switching careers.
Recheck durations on Coursera before locking your final learning timeline, since course metadata can change over time.

Globalize AWS agent plugins for Codex

Wed, 22 Apr 2026 08:00:00 GMT

import { Aside, Steps, Tabs, TabItem, Collapse } from 'astro-pure/user' import { LinkPreview } from 'astro-pure/advanced'

Why globalize the plugin setup?

If you install the marketplace in repo-local mode, Codex only sees the plugins when you open the exact repository that contains:

$REPO_ROOT/.agents/plugins/marketplace.json

That is fine while developing the plugin itself. But if your goal is to:

reuse the same plugins across many repositories
keep one stable AWS plugin set for every workspace
avoid opening the agent-plugins repo just to see the plugins in Plugin Directory

then you should move to a personal marketplace at:

~/.agents/plugins/marketplace.json

The setup we want

We will follow the safest option:

Clone the upstream repo from awslabs/agent-plugins
Take the AWS plugins you want from plugins/
Copy them into a global root under your home directory
Create ~/.agents/plugins/marketplace.json
Restart Codex and verify the plugins appear in every repo

After that, your structure should look like this:

C:\Users\<you>\.agents\plugins\
├── marketplace.json
└── agent-plugins-for-aws\
    └── plugins\
        ├── amazon-location-service\
        ├── aws-amplify\
        ├── aws-serverless\
        ├── databases-on-aws\
        ├── deploy-on-aws\
        ├── migration-to-aws\
        └── sagemaker-ai\

Step 1: Clone the upstream repository

If you do not already have the source locally, clone the official repo:

git clone https://github.com/awslabs/agent-plugins.git
cd agent-plugins

If your only goal is to use the plugins, you do not need to actively develop in this repo. You only need it as the source for the runtime plugin folders.

What exactly should you take from the repo?

For each plugin, copy the entire plugin directory under plugins/.

For example:

plugins/amazon-location-service/
plugins/aws-amplify/
plugins/aws-serverless/
plugins/databases-on-aws/
plugins/deploy-on-aws/
plugins/migration-to-aws/
plugins/sagemaker-ai/

Why copy the whole directory instead of only plugin.json?

the plugin needs .codex-plugin/plugin.json
many plugins depend on skills/
many plugins depend on .mcp.json
some plugins also rely on hooks/, scripts/, or reference material used by their skills

Step 2: Create a global plugin root

On Windows, create the global directory like this:

$GlobalRoot = "$HOME\\.agents\\plugins\\agent-plugins-for-aws"
New-Item -ItemType Directory -Force -Path "$GlobalRoot\\plugins" | Out-Null

Then copy the plugins you want:

Copy-Item -Recurse -Force .\plugins\amazon-location-service "$GlobalRoot\\plugins\\"
Copy-Item -Recurse -Force .\plugins\aws-amplify "$GlobalRoot\\plugins\\"
Copy-Item -Recurse -Force .\plugins\aws-serverless "$GlobalRoot\\plugins\\"
Copy-Item -Recurse -Force .\plugins\databases-on-aws "$GlobalRoot\\plugins\\"
Copy-Item -Recurse -Force .\plugins\deploy-on-aws "$GlobalRoot\\plugins\\"
Copy-Item -Recurse -Force .\plugins\migration-to-aws "$GlobalRoot\\plugins\\"
Copy-Item -Recurse -Force .\plugins\sagemaker-ai "$GlobalRoot\\plugins\\"

If you only need a subset, copy only those plugin folders.

Step 3: Create the global marketplace

Create this file:

C:\Users\<you>\.agents\plugins\marketplace.json

with content like this:

{
  "name": "agent-plugins-for-aws",
  "interface": {
    "displayName": "Agent Plugins for AWS"
  },
  "plugins": [
    {
      "name": "amazon-location-service",
      "source": {
        "source": "local",
        "path": "./agent-plugins-for-aws/plugins/amazon-location-service"
      },
      "policy": {
        "installation": "AVAILABLE",
        "authentication": "ON_INSTALL"
      },
      "category": "Location"
    },
    {
      "name": "aws-amplify",
      "source": {
        "source": "local",
        "path": "./agent-plugins-for-aws/plugins/aws-amplify"
      },
      "policy": {
        "installation": "AVAILABLE",
        "authentication": "ON_INSTALL"
      },
      "category": "Full Stack"
    },
    {
      "name": "aws-serverless",
      "source": {
        "source": "local",
        "path": "./agent-plugins-for-aws/plugins/aws-serverless"
      },
      "policy": {
        "installation": "AVAILABLE",
        "authentication": "ON_INSTALL"
      },
      "category": "Development"
    },
    {
      "name": "databases-on-aws",
      "source": {
        "source": "local",
        "path": "./agent-plugins-for-aws/plugins/databases-on-aws"
      },
      "policy": {
        "installation": "AVAILABLE",
        "authentication": "ON_INSTALL"
      },
      "category": "Database"
    },
    {
      "name": "deploy-on-aws",
      "source": {
        "source": "local",
        "path": "./agent-plugins-for-aws/plugins/deploy-on-aws"
      },
      "policy": {
        "installation": "AVAILABLE",
        "authentication": "ON_INSTALL"
      },
      "category": "Deployment"
    },
    {
      "name": "migration-to-aws",
      "source": {
        "source": "local",
        "path": "./agent-plugins-for-aws/plugins/migration-to-aws"
      },
      "policy": {
        "installation": "AVAILABLE",
        "authentication": "ON_INSTALL"
      },
      "category": "Migration"
    },
    {
      "name": "sagemaker-ai",
      "source": {
        "source": "local",
        "path": "./agent-plugins-for-aws/plugins/sagemaker-ai"
      },
      "policy": {
        "installation": "AVAILABLE",
        "authentication": "ON_INSTALL"
      },
      "category": "AI"
    }
  ]
}

The most important part here is source.path:

it should always start with ./
it is resolved relative to the directory containing marketplace.json
that is why ./agent-plugins-for-aws/plugins/... correctly points at the global plugin tree you copied

Step 4: Verify the plugin tree before opening Codex

Each plugin should have at least:

.codex-plugin/plugin.json
skills/
.mcp.json if the plugin depends on MCP servers

You can verify that quickly with PowerShell:

$MarketRoot = "$HOME\\.agents\\plugins"
$Plugins = @(
  "amazon-location-service",
  "aws-amplify",
  "aws-serverless",
  "databases-on-aws",
  "deploy-on-aws",
  "migration-to-aws",
  "sagemaker-ai"
)

$Plugins | ForEach-Object {
  $Path = Join-Path $MarketRoot "agent-plugins-for-aws\\plugins\\$_"
  [PSCustomObject]@{
    Name = $_
    PluginDir = Test-Path $Path
    CodexManifest = Test-Path (Join-Path $Path ".codex-plugin\\plugin.json")
    Skills = Test-Path (Join-Path $Path "skills")
    McpConfig = Test-Path (Join-Path $Path ".mcp.json")
  }
} | Format-Table -AutoSize

If every column shows True, your global plugin tree is usable.

Step 5: Restart Codex and confirm the plugins appear everywhere

Once ~/.agents/plugins/marketplace.json exists, restart Codex so it reloads the personal marketplace.

Then open any other repo that has nothing to do with AWS plugins. That is the real test. If the plugins still appear in Plugin Directory there, your global setup is correct.

If the plugins only show up when you open the agent-plugins repo, you are still using the repo-local marketplace instead of the personal one.

Do you still need to keep the original repo?

Not necessarily.

Once you have copied the plugin folders you need into ~/.agents/plugins/agent-plugins-for-aws/, Codex reads from there. The original repo becomes:

a place to pull upstream updates later
a place to inspect source or contribute back to awslabs/agent-plugins

If you are not tracking upstream actively, your runtime setup no longer depends on the original repository.

When should you not use this approach?

Copying plugin folders into a global root is the simplest setup, but not always the right one.

You may not want it if:

you are actively developing the plugins every day and want changes reflected straight from the dev repo
you often switch branches or test unfinished plugin work
you prefer a symlink-based or automated sync workflow

In those cases, a repo-local marketplace or a sync script may be a better fit.

Common failure cases

1. The marketplace appears, but install is broken

The usual reason is that source.path points at a folder that exists by name but is missing runtime files such as:

.codex-plugin/plugin.json
skills/
.mcp.json

2. The plugins only appear in one repo

That usually means the marketplace still lives at:

$REPO_ROOT/.agents/plugins/marketplace.json

instead of:

~/.agents/plugins/marketplace.json

3. You changed files, but Codex does not see the update yet

Codex often needs a restart to reload the personal marketplace and refresh the local plugin cache.

The full flow in one checklist

If you want the most stable and least surprising way to globalize AWS agent plugins for Codex, the recipe is:

This is not the most elegant workflow in a DRY sense, but it is the least fragile. You separate the runtime plugin tree from the development repo, keep a clear global marketplace, and stop depending on opening one specific repo just so Codex can see your plugins.

References

free-coding-models — Find the Fastest Coding LLM in Seconds

Wed, 18 Mar 2026 08:00:00 GMT

import { Aside, Tabs, TabItem, Collapse, Steps } from 'astro-pure/user'

Introduction

free-coding-models is a real-time TUI tool that pings 160 coding models from 20 providers simultaneously, helping you find the fastest LLM for your AI coding assistant.

Contributors

vava-nessa · erwinh22 · whit3rabbit · skylaweber · PhucTruong-ctrl

💬 Let's talk about the project on Discord

By Vanessa Depraute

1. Create a free API key (NVIDIA, OpenRouter, Hugging Face, etc.)
2. npm i -g free-coding-models
3. free-coding-models

Find the fastest coding LLM models in seconds

Ping free coding models from 20 providers in real-time — pick the best one for OpenCode, OpenClaw, or any AI coding assistant

⚠️ Beta notice
FCM Proxy V2 support for external tools is still in beta. Claude Code, Codex, Gemini, and the other proxy-backed launchers already work in many setups, but auth and startup edge cases can still fail while the integration stabilizes.

✨ Features
📋 Requirements
📦 Installation
🚀 Usage
📊 TUI Columns
📐 Stability Score
📡 FCM Proxy V2
🤖 Coding Models
🔌 OpenCode Integration
🦞 OpenClaw Integration
⚙️ How it works

✨ Features

🎯 Coding-focused — Only LLM models optimized for code generation, not chat or vision
🌐 Multi-provider — Models from NVIDIA NIM, Groq, Cerebras, SambaNova, OpenRouter, Hugging Face Inference, Replicate, DeepInfra, Fireworks AI, Codestral, Hyperbolic, Scaleway, Google AI, SiliconFlow, Together AI, Cloudflare Workers AI, Perplexity API, Alibaba Cloud (DashScope), ZAI, and iFlow
⚙️ Settings screen — Press P to manage provider API keys, enable/disable providers, access FCM Proxy V2 settings, and check/install updates
📡 FCM Proxy V2 — Built-in reverse proxy with multi-key rotation, rate-limit failover, and Anthropic wire format translation for Claude Code. Optional always-on background service keeps the proxy running 24/7
🚀 Parallel pings — All models tested simultaneously via native fetch
📊 Real-time animation — Watch latency appear live in alternate screen buffer
🏆 Smart ranking — Top 3 fastest models highlighted with medals 🥇🥈🥉
⏱ Adaptive monitoring — Starts in a fast 2s cadence for 60s, settles to 10s, slows to 30s after 5 minutes idle, and supports a forced 4s mode
📈 Rolling averages — Avg calculated from ALL successful pings since start
📊 Uptime tracking — Percentage of successful pings shown in real-time
📐 Stability score — Composite 0–100 score measuring consistency (p95, jitter, spikes, uptime)
📊 Token usage tracking — The proxy logs prompt+completion token usage per exact provider/model pair
📜 Request Log Overlay — Press X to inspect recent proxied requests and token usage
📋 Changelog Overlay — Press N to browse all versions in an index
🛠 MODEL_NOT_FOUND Rotation — If a provider returns 404, the TUI rotates through other providers for the same model
🔄 Auto-retry — Timeout models keep getting retried
🎮 Interactive selection — Navigate with arrow keys, press Enter to act
💻 OpenCode integration — Auto-detects NIM setup, sets model as default, launches OpenCode
🦞 OpenClaw integration — Sets selected model as default provider
🧰 Public tool launchers — 13 tool modes: OpenCode CLI, OpenCode Desktop, OpenClaw, Crush, Goose, Aider, Claude Code, Codex, Gemini, Qwen, OpenHands, Amp, and Pi
🔌 Install Endpoints flow — Press Y to install providers into tools
📝 Feature Request (J key) — Send anonymous feedback
🐛 Bug Report (I key) — Send anonymous bug reports
📶 Status indicators — UP ✅ · No Key 🔑 · Timeout ⏳ · Overloaded 🔥 · Not Found 🚫
🏷 Tier filtering — Filter models by tier letter (S, A, B, C)
⭐ Persistent favorites — Press F to pin/unpin models

📋 Requirements

Before using free-coding-models, make sure you have:

Node.js 18+ — Required for native fetch API
At least one free API key — pick any of the providers below

Provider Setup Links

| Provider | Free Tier | Link | |----------|-----------|------| | NVIDIA NIM | 40 req/min | build.nvidia.com | | Groq | 30-50 RPM | console.groq.com/keys | | Cerebras | Generous dev tier | cloud.cerebras.ai | | SambaNova | Dev tier generous | sambanova.ai/developers | | OpenRouter | 50-1000 req/day on :free | openrouter.ai/keys | | Hugging Face | Free monthly credits | huggingface.co/settings/tokens | | Replicate | 6 req/min | replicate.com/account/api-tokens | | DeepInfra | 200 concurrent | deepinfra.com/login | | Fireworks AI | $1 free credits | fireworks.ai | | Mistral Codestral | 30 req/min | codestral.mistral.ai | | Hyperbolic | $1 free trial | app.hyperbolic.ai/settings | | Scaleway | 1M free tokens | console.scaleway.com/iam/api-keys | | Google AI Studio | 14.4K req/day | aistudio.google.com/apikey | | SiliconFlow | Varies by model | cloud.siliconflow.cn/account/ak | | Together AI | Credits/promotions | api.together.ai/settings/api-keys | | Cloudflare Workers AI | 10k neurons/day | dash.cloudflare.com | | Perplexity API | Tiered by spend | perplexity.ai/settings/api | | ZAI | Coding Plan subscription | z.ai | | Alibaba Cloud (DashScope) | 1M free tokens | modelstudio.console.alibabacloud.com |

OpenRouter Free Tier Details

OpenRouter provides free requests on free models (:free):

No credits (or {'<'}$10): 50 requests/day (20 req/min)
≥ $10 in credits: 1000 requests/day (20 req/min)

Key things to know:

Free models (:free) never consume your credits
Failed requests still count toward your daily quota
Quota resets every day at midnight UTC

📦 Installation

Or use directly with npx/pnpx/bunx:

npx free-coding-models
pnpx free-coding-models
bunx free-coding-models

🆕 What's New

Version 0.3.5 fixes the main Claude Code proxy compatibility bug:

Claude Code beta-route requests now work — the proxy accepts Anthropic URLs like /v1/messages?beta=true
The fix was validated against the real claude binary

🚀 Usage

# Just run it — starts in OpenCode CLI mode
free-coding-models

# Explicitly target OpenCode CLI
free-coding-models --opencode

# Explicitly target OpenCode Desktop
free-coding-models --opencode-desktop

# Explicitly target OpenClaw
free-coding-models --openclaw

# Launch other supported tools
free-coding-models --crush
free-coding-models --goose
free-coding-models --aider
free-coding-models --claude-code

# Show only top-tier models (A+, S, S+)
free-coding-models --best

# Analyze for 10 seconds and output the most reliable model
free-coding-models --fiable

# Output results as JSON
free-coding-models --json

# Filter by tier
free-coding-models --tier S          # S+ and S only
free-coding-models --tier A          # A+, A, A- only

# Combine flags freely
free-coding-models --openclaw --tier S
free-coding-models --opencode --best

Setup Wizard (First Run)

On first run, you'll be walked through all 20 providers:

🔑 First-time setup — API keys
Enter keys for any provider you want to use. Press Enter to skip.

● NVIDIA NIM
  Free key at: https://build.nvidia.com
  Profile → API Keys → Generate
Enter key (or Enter to skip): nvapi-xxxx

● Groq
  Free key at: https://console.groq.com/keys
  API Keys → Create API Key
Enter key (or Enter to skip): gsk_xxxx

Adding or Changing Keys Later

Press P to open the Settings screen at any time:

↑↓ — navigate providers
Enter — edit the selected key
Space — toggle provider enabled/disabled
T — test the key with a live ping
Esc — close settings

Keys are saved to ~/.free-coding-models.json (permissions 0600).

Environment Variable Overrides

Env vars always take priority over the config file:

NVIDIA_API_KEY=nvapi-xxx free-coding-models
GROQ_API_KEY=gsk_xxx free-coding-models
OPENROUTER_API_KEY=sk-or-xxx free-coding-models

📊 TUI Columns

The main table displays one row per model with the following columns:

| Column | Sort Key | Description | |--------|----------|-------------| | Rank | R | Position based on current sort (medals 🥇🥈🥉 for top 3) | | Tier | — | SWE-bench tier (S+, S, A+, A, A-, B+, B, C) | | SWE% | S | SWE-bench Verified score — industry-standard for coding | | CTX | C | Context window size (e.g. 128k) | | Model | M | Model display name (favorites show ⭐ prefix) | | Provider | O | Provider name (NIM, Groq, etc.) | | Latest Ping | L | Most recent round-trip latency in milliseconds | | Avg Ping | A | Rolling average of ALL successful pings since launch | | Health | H | Current status: UP ✅, NO KEY 🔑, Timeout ⏳, Overloaded 🔥 | | Verdict | V | Health verdict based on avg latency + stability | | Stability | B | Composite 0–100 consistency score | | Up% | U | Uptime — percentage of successful pings | | Used | — | Total tokens consumed for this provider/model pair |

Verdict Values

| Verdict | Meaning | |---------|---------| | Perfect | Avg < 400ms with stable p95/jitter | | Normal | Avg < 1000ms, consistent responses | | Slow | Avg 1000–2000ms | | Spiky | Good avg but erratic tail latency | | Very Slow | Avg 2000–5000ms | | Overloaded | Server returned 429/503 | | Unstable | Was up but now timing out, or avg > 5000ms | | Not Active | No successful pings yet | | Pending | First ping still in flight |

📐 Stability Score

The Stability column shows a composite 0–100 score that answers: "How consistent and predictable is this model?"

Average latency alone is misleading — a model averaging 250ms that randomly spikes to 6 seconds feels slower than a steady 400ms model.

Formula

Stability = 0.30 × p95_score
          + 0.30 × jitter_score
          + 0.20 × spike_score
          + 0.20 × reliability_score

| Component | Weight | What it measures | |-----------|--------|-----------------| | p95 latency | 30% | Tail-latency spikes — the worst 5% of responses | | Jitter (σ) | 30% | Erratic response times — standard deviation | | Spike rate | 20% | Fraction of pings above 3000ms | | Reliability | 20% | Uptime — fraction of successful HTTP 200 pings |

📡 FCM Proxy V2

free-coding-models includes a local reverse proxy that merges all your provider API keys into one endpoint.

Disabled by default — enable in Settings (P) → FCM Proxy V2 settings.

What the Proxy Does

| Feature | Description | |---------|-------------| | Unified endpoint | One URL (http://127.0.0.1:18045/v1) replaces 20+ provider endpoints | | Key rotation | Automatically swaps to the next API key when one hits rate limits (429) | | Usage tracking | Tracks token consumption per provider/model pair in real-time | | Anthropic translation | Claude Code sends POST /v1/messages — proxy translates to OpenAI format | | Path normalization | Converts non-standard API paths to standard /v1/ calls |

Quick Setup

Via TUI:

Press P to open Settings
Select FCM Proxy V2 settings and press Enter
Enable Proxy mode, then select Install background service

Via CLI:

free-coding-models daemon install     # Install + start as OS service
free-coding-models daemon status      # Check running status
free-coding-models daemon restart     # Restart after config changes
free-coding-models daemon stop        # Graceful stop
free-coding-models daemon logs        # Show recent service logs

Platform Support

| Platform | Service Type | |----------|-------------| | macOS | launchd LaunchAgent | | Linux | systemd user service | | Windows | Falls back to in-process proxy |

🤖 Coding Models

160 coding models across 20 providers and 8 tiers, ranked by SWE-bench Verified.

Tier Scale

S+/S — Elite frontier coders (≥60% SWE-bench), best for complex real-world tasks
A+/A — Great alternatives, strong at most coding tasks
A-/B+ — Solid performers, good for targeted programming tasks
B/C — Lightweight or older models, good for code completion

Filtering by Tier

free-coding-models --tier S     # Only S+ and S (frontier models)
free-coding-models --tier A     # Only A+, A, A- (solid performers)
free-coding-models --tier B     # Only B+, B (lightweight options)
free-coding-models --tier C     # Only C (edge/minimal models)

Top Models by Provider

Alibaba Cloud (DashScope) — 8 models:

S+: Qwen3 Coder Plus (69.6%), Qwen3 Coder 480B (70.6%)
S: Qwen3 Coder Max (67.0%), Qwen3 235B (70.0%)
A+: Qwen3 32B (50.0%)
A: Qwen2.5 Coder 32B (46.0%)

ZAI Coding Plan — 5 models:

S+: GLM-5 (77.8%), GLM-4.5 (75.0%), GLM-4.7 (73.8%)

NVIDIA NIM — 44 models:

S+: GLM 5 (77.8%), Kimi K2.5 (76.8%), DeepSeek V3.2 (73.1%)
S: DeepSeek V3.1 Terminus (68.4%), Llama 4 Maverick (62.0%)
A+: Mistral Large 675B (58.0%), QwQ 32B (50.0%)
A: Llama 3.1 405B (44.0%), R1 Distill 32B (43.9%)

Groq — 10 models:

S: Kimi K2 Instruct (65.8%), Llama 4 Maverick (62.0%)
A+: QwQ 32B (50.0%)
A: Llama 3.3 70B (39.5%)

🔌 OpenCode Integration

The easiest way — let free-coding-models do everything:

Run: free-coding-models --opencode
Wait for models to be pinged (green ✅ status)
Navigate with ↑↓ arrows to your preferred model
Press Enter — tool automatically:
- Detects if NVIDIA NIM is configured in OpenCode
- Sets your selected model as default
- Launches OpenCode with the model pre-selected

tmux Sub-agent Panes

When launched from an existing tmux session, free-coding-models auto-adds an OpenCode --port argument so OpenCode can spawn sub-agents in panes.

You can force a specific port:

OPENCODE_PORT=4098 free-coding-models --opencode

ZAI Provider Proxy

OpenCode doesn't natively support ZAI's API path format. When you select a ZAI model, free-coding-models automatically starts a local reverse proxy that translates OpenCode's standard /v1/* requests to ZAI's API.

🦞 OpenClaw Integration

OpenClaw is an autonomous AI agent daemon. free-coding-models can configure it to use NVIDIA NIM models as its default provider.

Quick Start

free-coding-models --openclaw

Wait for models to be pinged
Navigate with ↑↓ arrows to your preferred model
Press Enter — tool automatically:
- Reads ~/.openclaw/openclaw.json
- Adds the nvidia provider block if missing
- Sets agents.defaults.model.primary to nvidia/<model-id>
- Saves config and prints next steps

Patching OpenClaw for Full NVIDIA Support

By default, OpenClaw only allows a few specific NVIDIA models. To add ALL 47 NVIDIA models:

# From the free-coding-models package directory
node patch-openclaw.js

This script:

Backs up existing config files
Adds all 47 NVIDIA models with proper context window and token limits
Preserves existing models and configuration

After patching, restart OpenClaw gateway:

systemctl --user restart openclaw-gateway

⚙️ How It Works

┌──────────────────────────────────────────────────────────────────┐
│  1. Enter alternate screen buffer (like vim/htop/less)           │
│  2. Ping ALL models in parallel                                  │
│  3. Display real-time table with Latest/Avg/Stability/Up%        │
│  4. Re-ping ALL models at 2s on startup, then 10s steady-state   │
│  5. Update rolling averages + stability scores per model         │
│  6. User can navigate with ↑↓ and select with Enter              │
│  7. On Enter: set model, launch selected tool                    │
│  8. Interface stays open until you select or press Ctrl+C        │
└──────────────────────────────────────────────────────────────────┘

Result: Continuous monitoring interface with rolling averages, stability scores, and one-keystroke tool configuration.

🔧 Keyboard Shortcuts

Main TUI

| Key | Action | |-----|--------| | ↑↓ | Navigate models | | Enter | Select model and launch current target tool | | R/S/C/M/O/L/A/H/V/B/U | Sort by Rank/SWE/Ctx/Model/Provider/Latest/Avg/Health/Verdict/Stability/Up% | | F | Toggle favorite on selected model (⭐ pinned at top) | | T | Cycle tier filter (All → S+ → S → A+ → A → ...) | | D | Cycle provider filter (All → NIM → Groq → ...) | | E | Toggle configured-only mode (persisted across sessions) | | Z | Cycle target tool (OpenCode → OpenClaw → Crush → ...) | | X | Toggle request logs (recent proxied requests) | | P | Open Settings (manage API keys, updates, profiles) | | Y | Open Install Endpoints flow | | Shift+P | Cycle through saved profiles | | Shift+S | Save current TUI settings as a named profile | | Q | Open Smart Recommend overlay | | N | Open Changelog overlay | | W | Cycle ping mode (FAST 2s → NORMAL 10s → SLOW 30s → FORCED 4s) | | J | Open FCM Proxy V2 settings | | I | Send feedback or bug reports | | K / Esc | Show help / Close overlay | | Ctrl+C | Exit |

Settings Screen (P Key)

| Key | Action | |-----|--------| | ↑↓ | Navigate providers, maintenance, profiles | | Enter | Edit API key, check/install update, load profile | | Space | Toggle provider enabled/disabled | | T | Test current provider's API key | | U | Check for updates manually | | Backspace | Delete the selected profile | | Esc | Close settings |

📋 Config Profiles

Profiles let you save and restore different TUI configurations — useful if you switch between work/personal setups or different tier preferences.

What's stored:

Favorites (starred models)
Sort column and direction
Tier filter
Ping mode
Configured-only filter
API keys

Saving a profile:

Configure the TUI the way you want
Press Shift+S — an inline prompt appears
Type a name (e.g. work, fast-only) and press Enter

Switching profiles:

Shift+P in the main table — cycles through saved profiles
--profile <name> — load a specific profile on startup

📄 License

MIT © vava

📬 Contribute

We welcome contributions! Feel free to open issues, submit pull requests, or get involved in the project.

Q: Can I use this with other providers?
A: Yes, the tool is designed to be extensible.

Q: How accurate are the latency numbers?
A: They represent average round-trip times measured during testing; actual performance may vary based on network conditions.

Q: Do I need to download models locally for OpenClaw?
A: No — free-coding-models configures OpenClaw to use NVIDIA NIM's remote API. No GPU or local setup required.

📧 Support

For questions or issues, open a GitHub issue.

💬 Let's talk about the project on Discord: https://discord.gg/ZTNFHvvCkU

Built with ☕ and 🌹 by vava

We collect anonymous usage data to improve the tool and fix bugs. No personal information is ever collected.

NAB Technical Interview Log

Mon, 16 Mar 2026 11:00:00 GMT

import { Aside, Steps, Collapse } from 'astro-pure/user'

Why I'm writing this interview log

There are interviews that, once they're over, leave your brain in a state of: "wait, what did I just answer?".

That's why I want to document everything that was asked during the NAB batch 18-2 technical round. The goal isn't to show off whether I got hard or easy questions, but to turn this interview into a genuinely useful review resource for next time.

Overview of the technical round

The interview wasn't just about code. Questions spanned from:

self-introduction in English
communication and past team lead experience
computer science fundamentals
data structures and algorithms
networking and infrastructure
databases, especially PostgreSQL
a small coding exercise with stacks

This shows they're not looking for someone who just writes APIs. They want to check if a candidate has the perspective of a backend engineer.

1. English and background

The opening was a self-introduction in English. This part seems light but is actually quite important, because the interviewer will dig into every detail from your CV.

What I was asked about

My current tech stack
Projects listed on my CV
Places I've interned
My actual roles in those projects

Then the interviewer moved into communication since my CV mentioned I had taken on a tech lead role during an internship.

Questions diving into communication

They asked about how I led the team, specifically:

how I divided tasks
how I supported blocked team members
how I handled coordination within the team

This doesn't require a fancy answer. What they want to see is whether you've actually worked with people, or if you just wrote "tech lead" on your CV to look cool like a leather jacket in a movie.

2. Infrastructure: it's rough when backend doesn't know infra

Since my CV mentioned:

participating in AWS FCAJ
having a homelab server

the interviewer continued with cloud and infrastructure questions.

What they wanted to hear

How a backend developer practices with cloud
What I've done with my home server
Whether I understand deployment, networking, reverse proxy, DNS

The interesting point was the interviewer's comment:

Even as backend, infrastructure knowledge is no less important.

I found this very correct. In many environments, backend can't just know ORM, controller, and service layer. Just one day of having to deploy an app, debug SSL, handle reverse proxy, or figure out why a request isn't reaching the server, and you're already in infra territory.

3. Computer Science: process, thread, and memory

After the background section, the interview moved to foundational knowledge.

Process and thread

Questions included:

What is a process
What is a thread
How a process contains multiple threads
How they share resources

The concise understanding:

Process is a running program with its own memory space
Thread is an execution flow within a process
A process can contain multiple threads
Threads within the same process typically share the process's common memory

Intel Hyper-Threading

The interviewer also asked about Intel Hyper-Threading. This is the type of question used to see if a candidate understands parallelism at a foundational level.

The key points:

one physical core can behave like multiple logical threads
the goal is to utilize CPU resources better
it doesn't turn 1 core into 2 real cores, but it helps the pipeline avoid being wasted in many situations

Memory allocation

This part tied into the process and thread discussion:

processes have their own memory space
threads share part of the process's memory
stack and heap are foundational concepts worth understanding clearly

4. DSA: ArrayList and LinkedList

This is a classic question group but very easy to answer incorrectly if you speak too fast.

What was asked

The "parent-child" relationship between list types
How memory is allocated
Time complexity when inserting elements

Quick comparison

ArrayList

allocates contiguous memory regions
fast random access
inserting in the middle usually requires shifting subsequent elements
therefore insert is typically O(n)

LinkedList

each node contains data and a reference to another node
memory doesn't need to be contiguous
if you already have a reference to the node to insert after, insert can be O(1)
but accessing the exact position usually requires traversal, so lookup is O(n)

5. Networking: from homelab to TLS termination

This is the part I found quite interesting because it's closer to real-world experience than textbook theory.

Public IP and Cloudflare Tunnel

Since my CV mentioned hosting a homelab server, the interviewer asked about:

Public IP
Cloudflare Tunnel

Key points:

With Public IP, the server can be exposed directly via router, port forwarding, and firewall rules
With Cloudflare Tunnel, internal services can be published externally without opening ports directly from the ISP to the server

This question doesn't just test definitions; it tests whether you've actually "played" with infrastructure.

DNS and how ISPs block websites

A pretty good question was:

How does an ISP block access to a website?

This is a very practical networking question. Some directions you could go:

blocking at the DNS layer
returning wrong DNS results or failing to resolve
blocking the destination IP
filtering traffic at different network layers

The good part is the interviewer didn't just ask "what is DNS" but asked about real-world use cases.

TLS termination, HTTPS, and HTTP

This part revolved around how HTTPS traffic is handled at the reverse proxy or edge layer.

A very typical flow is:

Client sends request over HTTPS
Reverse proxy or load balancer receives the TLS connection
That device decrypts the TLS
Traffic can be forwarded to the backend over internal HTTP or continue over HTTPS

This concept is called TLS termination.

SSL certificates and Let's Encrypt

When talking about HTTPS, the conversation naturally goes to SSL certificates and Let's Encrypt.

This is quite practical knowledge for anyone who has hosted apps:

you need a certificate for browsers to trust HTTPS connections
Let's Encrypt provides free certificates
it's commonly used with NGINX, Caddy, Traefik, or Cloudflare setups

6. Database: PostgreSQL and very "backend" questions

The database section focused on basic relational concepts and indexing.

Basic relational database concepts

Questions included:

table
record
row
column
composite key

This is knowledge that isn't hard but very easy to be complacent about. Technical interviews often like to take something that seems basic to see if a candidate can speak precisely.

Composite key

A composite key is a key created from multiple columns instead of a single column.

An easy-to-understand example is a many-to-many relationship table, where:

studentId
courseId

can be combined to form the primary key.

Indexing

The interviewer asked about:

Hash Index
B-tree Index

Hash Index

Suitable for equality queries like:

where email = 'a@example.com'

It's not strong for range queries.

B-tree Index

This is a much more common index type because it supports queries well:

=
>
<
between
order by in many situations

Why not automatically index everything?

This is a very backend and very practical question.

The reason is that indexes aren't free. They create a trade-off between read and write:

more indexes means faster reads in some queries
but insert, update, delete will incur additional cost to update the indexes

To put it humorously, the database isn't a saint. You can't tell it "I want fast reads, fast writes, and low resource usage, please balance it yourself".

7. Session pooling and Supabase

Since I mentioned Supabase in my CV, the interviewer followed up on connection pooling:

How should backend optimize to limit sessions?

This is a question that hits directly at building real applications.

The right way to think

don't open database connections recklessly
utilize connection pools appropriately
reduce unnecessary queries
batch queries if appropriate
cache where suitable
avoid letting each request create a bunch of new sessions

What the interviewer wants to see isn't just "knowing what pooling is", but understanding how to design backend to conserve connections and be more stable.

8. Coding: checking bracket strings with stack

The coding part was a familiar problem:

"{[()]}"

The requirement was to check if the bracket string is valid.

The idea

Use a stack:

when encountering an opening bracket, push onto the stack
when encountering a closing bracket, pop the top element to compare
if there's a mismatch or the stack is empty too soon, it's invalid
if you finish the string and the stack is empty, it's valid

C# Example

public static bool IsValid(string input)
{
    var stack = new Stack<char>();

    foreach (var ch in input)
    {
        if (ch == '(' || ch == '[' || ch == '{')
        {
            stack.Push(ch);
            continue;
        }

        if (stack.Count == 0)
        {
            return false;
        }

        var top = stack.Pop();

        var isMismatch =
            (ch == ')' && top != '(') ||
            (ch == ']' && top != '[') ||
            (ch == '}' && top != '{');

        if (isMismatch)
        {
            return false;
        }
    }

    return stack.Count == 0;
}

Why does this problem appear often?

Because it tests multiple things at once:

whether you understand stacks
whether you handle condition branches cleanly
whether you forget edge cases
whether you stay calm when coding live

9. What did I learn from this interview?

Looking back, I feel this interview reflects quite clearly the profile of a backend candidate that companies expect.

Not just code

You need the ability to talk about:

projects you've done
your actual role in the team
how you communicate and collaborate
how you view the system from infra to database

Not just memorizing definitions

Many questions don't stop at "define what X is" but go further to:

how it's used in practice
what the trade-offs are
how to optimize when facing constraints

Not just knowing frameworks

At some level, frameworks are just a layer of clothing. Underneath is still:

process
thread
memory
data structure
networking
database
problem solving

That's the real backbone.

10. Topics I should review after today

After this session, I want to review these areas more deeply:

process, thread, context switching, memory model
ArrayList and LinkedList according to their true data structure nature
DNS, TLS, reverse proxy, tunnel
PostgreSQL indexing strategy
connection pooling and session limits in backend services
stack / queue / string parsing interview-style problems

Conclusion

I like interviews like this because they show me very clearly one thing: backend isn't just writing APIs and waiting for frontend to call them. A good backend engineer needs a CS foundation, systems thinking, understanding of networking, databases, and also the ability to communicate with people.

The NAB batch 18-2 technical round is a fairly clear reminder that the backend learning journey is still much broader than what lies within a specific framework.

And yes, that bracket stack problem is definitely the type of problem that "looks innocent but makes your hands shake" when you're being stared at while coding.

9Router Combo Cheatsheet for Daily Use

Mon, 16 Mar 2026 08:00:00 GMT

import { Aside, Tabs, TabItem, Steps, Collapse } from 'astro-pure/user'

Why do I need a combo cheatsheet?

As the number of models grows, the question is no longer "which model is the most powerful" but which model fits best for each task.

With 9Router, I don't want to sit and remember every time I work:

which combo is good for fast coding
which combo is good for deep thinking
which combo is good for review
which combo is good for reading images or screenshots

This is a practical note to open and pick a combo in seconds.

How I categorize combos

Quick selection map

1. `coding-light`

Use when

daily coding
CRUD
fixing medium bugs
quick scaffolding
light refactoring
agent editing code continuously

Personality of this combo

This is a coder-first combo. The goal is to write code quickly and stably, without pulling in reasoning-heavy models for tasks that don't need that "heavy lifting".

Models

qw/qwen3-coder-plus — main coder, good balance between quality and speed
kr/qwen3-coder-next — good for agent coding, strong in multi-step flows
if/qwen3-coder-plus — backup coder from the same thinking family as Qwen coder
qw/qwen3-coder-flash — fastest in the group, good for small patches and short tasks

Mantra

Normal coding, no philosophy needed, just coding-light.

2. `coding-hard`

Use when

hard features
multi-file refactoring
tricky logic bugs
tasks needing both coding and thinking
agent must plan before fixing

Personality of this combo

This is engineering mode combo. It doesn't just write code; it has enough brain to think before producing patches.

Models

qw/qwen3-coder-plus — main code writer
kr/claude-sonnet-4.5 — planner/reviewer, strong at structure and explanation
if/deepseek-v3.2 — auxiliary reasoning, connects logic well
kr/qwen3-coder-next — supplementary coder, good for extended multi-step tasks

Mantra

Hard coding, many steps, need to think while doing → coding-hard.

3. `reasoning`

Use when

finding root causes
very hard debugging
analyzing long logs
debating solutions
complex algorithms or logic flows
not ready to code yet

Personality of this combo

This combo is for when you need to say:

Wait, don't fix yet. Sit down and think first.

Models

if/deepseek-r1 — digs deep into logic, great for finding root causes
if/kimi-k2 — holds long context, synthesizes lots of information
if/qwen3-max — balanced reasoning, versatile, easy to delegate
if/qwen3-235b-a22b-thinking-2507 — specialized deep thinker, good for critique and persistent thinking

Mantra

When the problem's cause isn't clear, don't touch code, use reasoning.

Choose reasoning first if you're in one of these situations:

Multiple hypotheses but don't know which is correct
Fixed several times but the bug keeps coming back
Very long logs involving many services or layers
You want the model to analyze before touching code

4. `architect`

Use when

writing specs
proposing architecture
dividing modules or services
selecting patterns
writing docs, proposals, design notes
comparing approaches

Personality of this combo

This combo is for design and expression. It's not aimed at producing quick patches, but at making good decisions and writing readable documentation.

Models

kr/claude-sonnet-4.5 — writes fluently, beautiful structure, great for design/spec
if/kimi-k2 — holds long context, good at synthesizing documents
if/qwen3-max — balanced between thinking and practicality
if/deepseek-r1 — logic critique, spots architecture holes

Mantra

Writing spec, design, proposal, or architecture notes → architect.

5. `eazy`

Use when

quick questions
text transformation
fixing short snippets
light brainstorming
casual chat
many small tasks

Personality of this combo

This is the fast lane combo. Not every task needs calling out the big brain council. Many tasks just need a fast, compact, smart-enough combo to get done.

Models

gc/gemini-3-flash-preview — very fast, good for Q&A and daily tasks
kr/claude-haiku-4.5 — compact, fast, stable for text and general chat
if/deepseek-v3.2 — fast but still has brain, good for slightly technical tasks
qw/qwen3-coder-flash — fast for code snippets or small patches

Mantra

Trivial tasks, need speed, no overkill → eazy.

6. `vision`

Use when

reading error screenshots
analyzing UI
viewing diagrams
images with text
looking at interfaces to infer flow or code

Personality of this combo

This combo is for everything with visual elements. When there are screenshots, UI, diagrams, or error photos, using the right vision combo helps models stop guessing from thin air.

Models

if/qwen3-vl-plus — main vision model, good for images and technical analysis
gc/gemini-3-pro-preview — strong multimodal, good for image + reasoning
qw/vision-model — vision fallback, adds a backup perspective

Mantra

Got images? Don't force text-only combos to guess. Just use vision.

7. `review`

Use when

reviewing PRs
auditing code
critiquing solutions
checking edge cases
spotting potential bugs
verifying output from other combos

Personality of this combo

This combo is for inspection. Not for creating the first solution, but for checking if that solution has anything suspicious.

Models

kr/claude-sonnet-4.5 — fluent review, clear comments, easy to read
if/deepseek-r1 — deep logic inspection, good for finding hidden bugs
if/qwen3-max — balanced reviewer, practical

Mantra

Already have a solution, now need to inspect it → review.

Practical workflows

Case 1: Building a backend feature

Start with coding-light.

If the task starts showing these signs:

many files
complex flow
agent needs to plan first
fixing one spot pulls three other spots

then upgrade to coding-hard.

Case 2: Hard bug

Start with reasoning to find the root cause.

Once the fix direction is clear, switch to coding-hard to produce the patch. This approach is often much better than "fixing by feeling".

Case 3: Writing architecture documentation

Use architect to establish the approach, select patterns, and write specs.

When the first draft is done, throw it to review for self-critique.

Case 4: Got a screenshot or image

Start with vision. After understanding the image or UI flow, if code fixes are needed, switch to coding-light or coding-hard.

Case 5: Have code but not fully confident

Use review. This is a valuable step when you want to check edge cases, code smells, or risks before merging.

Pocket note

coding-light  = daily coding
coding-hard   = hard coding, many steps
reasoning     = deep thinking, root cause
architect     = spec, design, proposal
eazy          = quick questions, small tasks
vision        = images, UI, screenshots
review        = inspect solutions / PRs / edge cases

Conclusion

The key isn't which model is the most powerful, but putting the right model in the right role.

This cheatsheet helps me reduce hesitation time when picking combos:

don't mistakenly call a thinker for quick coding
don't rush to throw coders at root cause problems
don't use casual chat combos for review
don't make text-only models guess from thin air when there are images

If you're also using multiple combos in 9Router, treat this as a mini playbook: open it, pick the right lane, then get to work.

9Router và headless coder agent

Sun, 15 Mar 2026 14:00:00 GMT

import { Aside, Steps, Tabs, TabItem, Collapse } from 'astro-pure/user' import { GithubCard, LinkPreview } from 'astro-pure/advanced'

Từ AI Supporting sang AI-Driven

Rất nhiều developer bắt đầu với kiểu dùng AI như một trợ lý gõ code:

GitHub Copilot để autocomplete
ChatGPT để hỏi logic
đôi lúc paste error vào chat rồi cầu nguyện

Kiểu này mình gọi là AI Supporting: dev vẫn suy nghĩ chính, AI chỉ hỗ trợ một phần nhỏ.

Khi chuyển sang AI-Driven, vai trò của AI đổi hẳn:

đọc codebase
đề xuất kế hoạch
sửa nhiều file
chạy command
lặp lại cho đến khi task hoàn thành

Đó là lý do các tool như Cline, Continue Agent, Codex CLI, hay các IDE như Kiro bắt đầu được chú ý mạnh. Chúng không chỉ viết vài dòng code cho đẹp đội hình. Chúng bắt đầu tham gia vào cả workflow phát triển phần mềm.

Headless coder agent là gì?

Khi nói "headless coder agent", mình đang nói tới nhóm công cụ có thể nhận một yêu cầu tự nhiên như:

Add Redis caching for the product API and update tests

rồi tự:

đọc repo
tìm file liên quan
sửa code
chạy build hoặc test
báo lại những gì đã thay đổi

Điểm quan trọng là: agent không phải LLM.

Một hệ thống AI coding thường có 3 lớp:

IDE / CLI
  ↓
Agent
  ↓
LLM hoặc Router

Trong đó:

Agent là thứ điều phối hành động
LLM là bộ não sinh ra reasoning và code
Router là lớp định tuyến model, fallback quota, gom nhiều provider vào một endpoint

9Router là gì?

9Router là một local AI router cung cấp OpenAI-compatible API tại local host, để các tool như Cline, Codex, Copilot, Cursor, OpenCode hay OpenClaw có thể gọi vào một endpoint duy nhất.

Theo README của project, luồng quick start cơ bản là:

chạy 9Router local
dashboard mở ở http://localhost:20128
API endpoint là http://localhost:20128/v1
kết nối provider trong dashboard
dùng endpoint đó trong tool AI của bạn

Điểm hấp dẫn nhất của 9Router là ý tưởng:

một endpoint duy nhất
nhiều provider phía sau
combo fallback khi hết quota hoặc lỗi

Vì sao lớp router này đáng giá?

Nếu không có router, workflow thường trông như sau:

Hết quota Claude
→ đổi extension
→ đổi provider
→ đổi API key
→ đổi model
→ mất context
→ hơi điên

Còn nếu có router:

VS Code / Cline
  ↓
9Router
  ↓
Claude / Gemini / Qwen / DeepSeek / ...

thì IDE chỉ biết một model alias hoặc một combo. Khi provider A hết quota, router có thể rơi xuống provider B.

Smart routing của 9Router thực sự là gì?

Đây là chỗ nhiều người mới rất dễ hiểu nhầm.

Trong trải nghiệm thực tế với UI hiện tại của 9Router:

Providers là nơi kết nối tài khoản hoặc credential
Proxy Pools là proxy mạng, không phải routing logic cho model
Combos mới là nơi bạn tạo chuỗi fallback / priority

Nói ngắn gọn:

Proxy Pools: HTTP/SOCKS proxy
Combos: ghép nhiều model theo thứ tự ưu tiên

Một combo kiểu code có thể trông như sau:

1. kr/claude-sonnet-4.5
2. kr/qwen3-coder-next
3. qw/qwen3-coder-plus
4. qw/qwen3-coder-flash

Khi đó request sẽ thử model đầu tiên trước. Nếu fail, timeout, hoặc hết quota, router sẽ rơi xuống model sau.

Một lưu ý rất quan trọng về "smart"

Tính đến tháng 3/2026, phần public docs của 9Router mô tả rất rõ:

OpenAI-compatible API
smart fallback
multi-provider routing
combo-based routing

Nhưng mình chưa thấy tài liệu chính thức public nào nói rõ rằng 9Router đang tự phân loại prompt theo ngữ nghĩa kiểu:

prompt code → Qwen
prompt reasoning → Claude
prompt ngắn → Gemini

Thứ có thật và dùng được ngay là:

fallback theo thứ tự
chia combo theo use case
map Plan/Act trong agent sang các combo khác nhau

Đây là khác biệt nhỏ nhưng quan trọng. Đừng kỳ vọng một "LLM thần thánh tự đoán mọi thứ". Hãy cấu hình theo ý đồ của mình.

Cline và Continue: khác nhau thế nào?

Cả Cline lẫn Continue đều có thể đóng vai trò AI coding assistant/agent trong VS Code, nhưng triết lý dùng hơi khác nhau.

Cline

Cline thiên về agentic workflow hơn:

đọc file
sửa file
chạy terminal
có tư duy Plan và Act
hỗ trợ OpenAI-compatible API

Điểm này khiến nó hợp với 9Router một cách gần như tự nhiên.

Continue

Continue linh hoạt hơn ở vai trò AI toolbox trong IDE:

autocomplete
edit
chat
agent mode
cấu hình nhiều provider và model khác nhau

Nếu bạn muốn một hệ sinh thái AI trong VS Code đa dạng hơn, Continue rất đáng thử. Nếu bạn muốn cảm giác "AI làm task rõ ràng, từng bước", Cline thường trực diện hơn.

Kiro IDE đứng ở đâu trong bức tranh này?

Kiro là một AI-native IDE xây trên Code OSS, nhấn mạnh vào spec-driven development. Theo tài liệu của họ, Kiro muốn đưa AI vào quy trình có cấu trúc hơn:

requirements
design
tasks
code

Điểm này khiến Kiro khác với kiểu "vibe coding rồi sửa sau". Nó cố gắng kéo AI từ trạng thái "viết code nhanh" sang "tham gia cả vòng đời triển khai".

Điều thú vị là: ngay cả khi bạn không dùng Kiro, bạn vẫn có thể học được từ triết lý đó và áp dụng vào VS Code + Cline + 9Router:

combo plan cho reasoning
combo code cho implementation
combo fast cho hỏi nhanh

Kiến trúc thực chiến mình khuyên dùng

Nếu bạn đang ở VS Code và muốn đi từ dễ tới mạnh, kiến trúc này khá hợp lý:

VS Code
  ├─ Cline
  ├─ Continue (optional)
  └─ Copilot (optional)
        ↓
      9Router
        ↓
   Combos / Providers
        ↓
Claude / Qwen / Gemini / DeepSeek / ...

Tư duy ở đây là:

Cline cho task execution
Continue cho chat/edit linh hoạt
9Router cho fallback và thống nhất endpoint

Cách nối Cline với 9Router

Ví dụ cấu hình trong Cline:

Provider: OpenAI Compatible
Base URL: http://localhost:20128/v1
API Key: <your-9router-key>
Model ID: code

Sau đó Cline sẽ không cần biết model thật ở phía sau là Claude, Qwen hay Gemini. Nó chỉ biết một cái tên như code.

Gợi ý 3 combo thực dụng

plan
1. kr/claude-sonnet-4.5
2. kr/deepseek-3.2
3. qw/qwen3-coder-plus

code
1. kr/qwen3-coder-next
2. qw/qwen3-coder-plus
3. qw/qwen3-coder-flash

fast
1. cline/gemini-3.1-flash-lite-preview
2. qw/qwen3-coder-flash

Tận dụng Plan / Act trong Cline

Nếu bạn dùng Cline, đây là pattern rất ngon:

Plan mode → plan
Act mode  → code

Ý tưởng:

khi cần suy nghĩ kiến trúc hoặc lập kế hoạch → dùng model reasoning mạnh
khi cần sửa code hàng loạt hoặc generate code → dùng model coding nhanh và rẻ hơn

Continue có nối với 9Router được không?

Có, miễn là workflow của bạn dùng OpenAI-compatible endpoint hoặc provider phù hợp. Ý tưởng giống hệt:

trỏ tới endpoint local của 9Router
dùng model alias hoặc combo từ router
để router xử lý fallback và quota

Nếu bạn thích Continue vì chat/edit/autocomplete đa dạng hơn, router vẫn có giá trị như cũ: gom mọi thứ về một endpoint.

Nên viết một bài hay nhiều bài?

Mình nghiêng về series 3 bài thay vì một bài all-in-one.

Bài 1 — bài nền tảng

9Router và headless coder agent Tập trung giải thích:

AI Supporting vs AI-Driven
agent là gì
router là gì
vì sao cần 9Router

Bài 2 — bài thực hành

Kết nối Cline/Continue với 9Router trên VS Code Tập trung vào:

cách cấu hình endpoint
model alias
combo
fallback
lỗi thường gặp

Bài 3 — bài chiến lược

Thiết kế workflow AI coding không lệ thuộc quota Tập trung vào:

plan/code/fast combo
đổi model mà không đổi IDE
cách phân vai reasoning và coding
khi nào dùng Cline, Continue, Kiro

Kết luận

Nếu phải tóm gọn toàn bộ câu chuyện trong một ý:

9Router không phải AI, mà là lớp router giúp các AI coding tool sống sót khi quota và provider trở mặt như người yêu cũ.

Còn headless coder agent là bước tiến từ kiểu dùng AI để autocomplete sang kiểu dùng AI để tham gia thật vào quy trình phát triển phần mềm.

Với setup đúng, bạn có thể giữ nguyên:

IDE
extension
workflow

nhưng thay đổi hoàn toàn độ linh hoạt phía sau bằng một local router và vài combo hợp lý.

Tài liệu chính thức nên đọc thêm

Running OpenClaw on ZimaOS with Portainer

Sun, 15 Mar 2026 08:00:00 GMT

import { Aside, Steps, Collapse } from 'astro-pure/user' import { GithubCard, LinkPreview } from 'astro-pure/advanced'

Why I Tried This

I wanted to run OpenClaw on a ZimaOS machine using Portainer and a single Docker Compose stack.

That sounds simple on paper, but ZimaOS is much more container-centric than a full Linux distro. In practice, that means the usual setup style of “run a helper script, create host folders, mount random paths under /home/...” is exactly where things start getting annoying.

So this post is not a generic OpenClaw introduction. It is a practical write-up of:

what OpenClaw is
why the default installation flow was not a good fit for my environment
what I changed for ZimaOS + Portainer
the compose stack that successfully got the gateway container started

What Is OpenClaw?

OpenClaw is an open-source coding agent project with an official Docker installation path and an official prebuilt container image published on GHCR.

The official Docker docs describe a setup built around:

openclaw-gateway
openclaw-cli

That matters, because there are also third-party images and downstream packaging variants floating around. If you want to stay close to upstream, start from the official image and official docs.

The Problem: Official Docker Flow vs ZimaOS Reality

The official docs assume a Docker environment where running helper scripts and onboarding commands is acceptable.

That is fine on a normal Linux box.

It is less fun on ZimaOS.

My constraints were:

no bash setup flow
no command-line-first installation
deployment through Portainer
avoid fragile host bind mounts when possible

This immediately pushed me toward a different strategy.

What I Found in the Repository

While checking the official repository and docs, one thing became clear: the repo contains multiple Docker-related files, but the important mental model is simpler than it first looks.

The main compose file is docker-compose.yml, while docker-compose.extra.yml is better understood as an override layer tied to the setup flow.

For a Portainer-first deployment, the practical move is to build a single self-contained compose stack that captures the parts you actually need without depending on the helper script.

The upstream Docker flow still leans on onboarding and CLI-oriented steps. For a container-centric NAS environment, that creates friction fast. I only wanted the minimum stable baseline first: pull the image, create the stack, publish the ports, and get the gateway booting.

The First Wrong Turn

My first instinct was to optimize for a future 9Router setup and prepare a shared external Docker network up front.

That looked clever.

It was not.

The moment I used an external network before that network actually existed, the stack stopped being smooth. On top of that, I still did not have 9Router running yet, so I was prematurely optimizing the architecture instead of just getting OpenClaw to boot.

The better move was to simplify:

remove the external-network dependency
use a normal bridge network
get openclaw-gateway into a stable starting state first
postpone the 9Router integration until later

The Compose Stack That Worked Better

This is the compose stack I ended up using as the practical baseline for ZimaOS + Portainer:

services:
  openclaw-gateway:
    image: ghcr.io/openclaw/openclaw:latest
    container_name: openclaw-gateway
    user: "1000:1000"
    environment:
      HOME: /home/node
      TERM: xterm-256color
      OPENCLAW_GATEWAY_TOKEN: "ocw_change_this_to_a_long_random_token"

    volumes:
      - openclaw-home:/home/node
      - openclaw-config:/home/node/.openclaw

    ports:
      - "18789:18789"
      - "18790:18790"

    init: true
    restart: unless-stopped

    command:
      - node
      - dist/index.js
      - gateway
      - --bind
      - lan
      - --port
      - "18789"

    networks:
      - ai-router

  openclaw-cli:
    image: ghcr.io/openclaw/openclaw:latest
    container_name: openclaw-cli
    user: "1000:1000"
    environment:
      HOME: /home/node
      TERM: xterm-256color
      OPENCLAW_GATEWAY_TOKEN: "ocw_change_this_to_a-long-random-token"

    volumes:
      - openclaw-home:/home/node
      - openclaw-config:/home/node/.openclaw

    network_mode: "service:openclaw-gateway"

    cap_drop:
      - NET_RAW
      - NET_ADMIN

    security_opt:
      - no-new-privileges:true

    profiles:
      - tools

networks:
  ai-router:
    driver: bridge

volumes:
  openclaw-home:
  openclaw-config:

Why This Version Makes More Sense

A few choices here are intentional.

Official image only

The image is:

ghcr.io/openclaw/openclaw:latest

That keeps the deployment aligned with upstream instead of a third-party packaging layer.

Named volumes over host bind mounts

For a container-first NAS-style environment, named volumes are simply less annoying. They avoid the classic “this path is read-only” or “why does this host directory not exist the way the script expects?” class of problems.

No external network yet

A shared external network is useful later, especially if I want OpenClaw to talk to a separate 9Router container through a stable service name.

But before that, it is just one more thing that can fail.

Gateway first, everything else later

The immediate milestone was not “full agent workflow with perfect onboarding.”

It was much simpler:

Can the stack pull the official image, create the container, publish the ports, and get the gateway into a valid starting state?

Once I saw the stack created successfully and openclaw-gateway in a starting state with published ports, that was already meaningful progress.

The Honest Caveat

This is the part that is easy to hide in a tutorial and much better to say out loud instead:

Even if the container starts correctly, you may still hit an authentication, pairing, or onboarding step later in the process.

That is not a ZimaOS-specific failure. It is part of the current Docker reality of this project.

What I Would Do Next

My next step would be to deploy 9Router in a separate container and then connect OpenClaw to it using a custom OpenAI-compatible provider configuration.

That is the kind of setup where a shared Docker network actually becomes useful. But it should be treated as a second phase after the base stack is stable.

Final Thoughts

This setup taught me something useful:

A lot of Docker tutorials assume a normal Linux machine with shell access, writable host paths, and patience for helper scripts.

ZimaOS changes that equation.

And that is exactly why a small, boring, upstream-aligned compose stack can be more valuable than a “feature-complete” setup that collapses under environmental assumptions.

If your goal is to experiment with OpenClaw on a container-centric home server, start from the minimum, prove the gateway boots, and then iterate from there.

That path is slower for about ten minutes and faster for the next three hours.

Tips to improve concentration

Sat, 10 May 2025 00:00:00 GMT

import { Aside } from 'astro-pure/user'

You're trying to concentrate, but your mind is wandering or you're easily distracted. What happened to the laser-sharp focus you once enjoyed? As we age, we tend to have more difficulty filtering out stimuli that are not relevant to the task at hand.

What's fogging up focus?

Like a computer that slows with use, the brain accumulates wear and tear that affects processing. This can be caused by a number of physiological stressors such as inflammation, injury to blood vessels (especially if you have high blood pressure), the buildup of abnormal proteins, and naturally occurring brain shrinkage.

The following factors can also affect your concentration.

Underlying conditions. Depression or sleep disorders (such as sleep apnea) can undermine your ability to concentrate. So can the effects of vision or hearing loss. You waste precious cognitive resources when you spend too much time trying to make out what's written on a page or just hear what someone is saying.

Medication side effects. Some drugs, especially anticholinergics (such as treatments for incontinence, depression, or allergies), can slow processing speed and your ability to think clearly.

Excessive drinking. Having too much alcohol impairs thinking and causes interrupted sleep, which affects concentration.

Information overload. We are bombarded with information from TVs, computers, and messages such as texts or emails. When there's too much material, it burdens our filtering system and it's easy to get distracted.

Strategies to stay focused

To improve attention, consider the following strategies.

Mindfulness. "Mindfulness is about focusing attention on the present moment, and practicing mindfulness has been shown to rewire the brain so that attention is stronger in everyday life," says Kim Willment, a neuropsychologist with Brigham and Women's Hospital. She recommends sitting still for a few minutes each day, closing your eyes, and focusing on your breathing as well as the sounds and sensations around you.

Cognitive training. Computerized cognitive training games aim to improve your response times and attention. Evidence that this works has been mixed. "The goal of playing these games is not to get better at them, but to get better in the cognitive activities of everyday life," Willment says. "But there is evidence that a person's ability to pay attention can be improved by progressively pushing the person to higher levels of performance. So if you reach a certain level of sustained attention, pushing it to the next level can help improve it, and this may translate to everyday life."

A healthier lifestyle. Many aspects of a healthy lifestyle can help attention, starting with sleep and exercise. There is a direct link between exercise and cognitive ability, especially attention. When you exercise, you increase the availability of brain chemicals that promote new brain connections, reduce stress, and improve sleep. And when we sleep, we reduce stress hormones that can be harmful to the brain, and we clear out proteins that injure it.

Aim for seven to eight hours of sleep each night, and 150 minutes per week of aerobic exercise, such as brisk walking.

Other healthy steps to improve focus: eat a Mediterranean-style diet, which has been shown to support brain health; treat underlying conditions; and change medications that may be affecting your ability to focus.

Getting older is out of your control, but healthier living is something you determine, and it may improve concentration.

Article from: Harvard Health Publishing

Using MDX

Sun, 01 Jun 2025 00:00:00 GMT

This theme comes with the @astrojs/mdx integration installed and configured in your astro.config.ts config file. If you prefer not to use MDX, you can disable support by removing the integration from your config file.

Why MDX?

MDX is a special flavor of Markdown that supports embedded JavaScript & JSX syntax. This unlocks the ability to mix JavaScript and UI Components into your Markdown content for things like interactive charts or alerts.

If you have existing content authored in MDX, this integration will hopefully make migrating to Astro a breeze.

Example

Here is how you import and use a UI component inside of MDX.
When you open this page in the browser, you should see the clickable button below.

import { Button } from 'astro-pure/user'

Click Me

What Is 3D Rendering? Complete Guide to 3D Visualization

Sun, 09 Feb 2025 00:00:00 GMT

3D rendering is all around us. From huge action movies to car commercials to previews of upcoming buildings or product designs, 3D visualization has become so widespread and realistic that you probably don’t even know it’s there.

In this introductory piece, Chaos’ Ricardo Ortiz explains the basics of 3D rendering, from the computational methods that create imagery to the artistic techniques that create great computer-generated (CG) content and its various uses.

What is 3D Rendering?

Put simply, 3D rendering is the process of using a computer to generate a 2D image from a digital three-dimensional scene.

To generate an image, specific methodologies and special software and hardware are used. Therefore, we need to understand that 3D rendering is a process—the one that builds the image.

Types of 3D rendering

We can create different types of rendered image; they can be realistic or non-realistic.

A realistic image could be an architectural interior that looks like a photograph, a product-design image such as a piece of furniture, or an automotive rendering of a car. On the other hand, we can create a non-realistic image such as an outline-type diagram or a cartoon-style image with a traditional 2D look. Technically, we can visualize anything we can imagine.

How is 3D rendering used?

3D rendering is an essential technique for many industries including architecture, product design, advertising, video games and visual effects for film, TV and animation.

In design and architecture, renders allow creative people to communicate their ideas in a clear and transparent way. A render gives them the chance to evaluate their proposals, experiment with materials, conduct studies and contextualize their designs in the real world before they are built or manufactured.

For the media and entertainment industries, 3D rendering is fundamental to the creation of sequences and animations that tell stories, whether we’re watching an animated movie, a period drama, or an action sequence with explosions, ships from the future, exotic locales, or extraterrestrial creatures.

Over the past few years, the evolution of computer graphics in these industries has replaced traditional techniques. For example, special effects are being replaced by visual effects, which means stunt people no longer risk their lives in car crashes.

In advertising, I would dare to say that 90% of automotive commercials are CG—or even more. In the architecture industry, many traditional techniques to create representations, such as scale models, have been replaced with photorealistic imagery to ensure we can see exactly how something will look once it’s built.

Accelerating processes, reducing costs and the demand for better quality results have helped technology evolve. Hardware is more powerful than ever and the switch to CG was inevitable.

How is a 3D rendered image generated?

Two pieces of software, with different characteristics, are used to computer-generate images and animations: render engines and game engines. Render engines use a technique called ray tracing, while game engines use a technique called rasterization—and some engines mix both techniques, but we will talk about that later on.

The Impact of Technology on the Music World

Sat, 30 Nov 2024 00:00:00 GMT

The evolution of music is a symphony of creativity, rhythm, and technology. From the humble beginnings of acoustic instruments to the present-day digital era, the relationship between music and technology has been transformative. In this article, we will explore the historical milestones, digital revolution, and emerging technologies that have shaped the music world. Join us on a journey through the chords of innovation as we discuss how technology has changed music.

Historical Perspective

The marriage of music and technology dates back centuries, with pivotal moments shaping the industry. The invention of the phonograph by Thomas Edison in the late 19th century marked the first time music could be recorded and replayed. Subsequent milestones, such as the electric guitar and the synthesizer, revolutionized music creation, paving the way for new genres and sounds.

These technological leaps didn't merely shape the musical landscape of their time but laid a foundation for the continuous evolution of the intersection between music and technology. As artists embraced these innovations, they unlocked new avenues for creativity, paving the way for diverse sounds and genres that have become integral to the vibrant tapestry of the modern music industry. The historical perspective illuminates the symbiotic relationship between music and technology, highlighting the transformative impact that each innovation has had on the way we create, consume, and experience music.

Digital Revolution

The digital revolution has been a seismic shift in the music industry, altering how music is consumed, distributed, and produced. The transition from physical formats like CDs and vinyl to digital formats such as MP3s and streaming services has democratized access to music. The ease of streaming has transformed how listeners discover and enjoy music, challenging traditional revenue models while offering unparalleled convenience.

Technology in Music Consumption and Distribution

Streaming services have become the heartbeat of music consumption, causing a decline in traditional music stores. The accessibility of music online has reshaped distribution channels, impacting both artists and record labels. While it provides exposure to a global audience, it also poses challenges regarding fair compensation for artists. The dynamics of the industry are evolving, reflecting the intricate dance between technology and music. Music Production and Creation

The advent of digital audio workstations (DAWs), software instruments, and electronic production techniques has democratized music creation. Artists now have powerful tools at their fingertips, enabling them to experiment with sounds, collaborate remotely, and produce music independently. This technological shift has broken down barriers, allowing for a diverse array of voices to be heard in the ever-expanding realm of music.

Markdown Syntax Support

Wed, 26 Jul 2023 08:00:00 GMT

Basic Syntax

Markdown is a lightweight and easy-to-use syntax for styling your writing.

Headers

When the content of the article is extensive, you can use headers to segment:

# Header 1

## Header 2

## Large Header

### Small Header

Header previews would disrupt the structure of the article, so they are not displayed here.

Bold and Italics

_Italic text_ and **Bold text**, together will be **_Bold Italic text_**

Preview:

Italic text and Bold text, together will be Bold Italic text

Links

Text link [Link Name](http://link-url)

Preview:

Text link Link Name

Inline Code

This is an `inline code`

Preview:

This is an inline code

Code Blocks

```js
// calculate fibonacci
function fibonacci(n) {
  if (n <= 1) return 1
  const result = fibonacci(n - 1) + fibonacci(n - 2) // [\!code --]
  return fibonacci(n - 1) + fibonacci(n - 2) // [\!code ++]
}
```

Preview:

// calculate fibonacci
function fibonacci(n) {
  if (n <= 1) return 1
  const result = fibonacci(n - 1) + fibonacci(n - 2) // [!code --]
  return fibonacci(n - 1) + fibonacci(n - 2) // [!code ++]
}

Currently using shiki as the code highlighting plugin. For supported languages, refer to Shiki: Languages.

Inline Formula

This is an inline formula $e^{i\pi} + 1 = 0$

Preview:

This is an inline formula $e^{i\pi} + 1 = 0$

Formula Blocks

$$
\hat{f}(\xi) = \int_{-\infty}^{\infty} f(x) e^{-2\pi i x \xi} \, dx
$$

Preview:

$$ \hat{f}(\xi) = \int_{-\infty}^{\infty} f(x) e^{-2\pi i x \xi} , dx $$

Currently using KaTeX as the math formula plugin. For supported syntax, refer to KaTeX Supported Functions.

Images

![CWorld](https://cravatar.cn/avatar/1ffe42aa45a6b1444a786b1f32dfa8aa?s=200)

Preview:

Strikethrough

~~Strikethrough~~

Preview:

~~Strikethrough~~

Lists

Regular unordered list

- 1
- 2
- 3

Preview:

Regular ordered list

1. GPT-4
2. Claude Opus
3. LLaMa

Preview:

GPT-4
Claude Opus
LLaMa

You can continue to nest syntax within lists.

Blockquotes

> Gunshot, thunder, sword rise. A scene of flowers and blood.

Preview:

Gunshot, thunder, sword rise. A scene of flowers and blood.

You can continue to nest syntax within blockquotes.

Line Breaks

Markdown needs a blank line to separate paragraphs.

If you don't leave a blank line
it will be in one paragraph

First paragraph

Second paragraph

Preview:

If you don't leave a blank line it will be in one paragraph

First paragraph

Second paragraph

Separators

If you have the habit of writing separators, you can start a new line and enter three dashes --- or asterisks ***. Leave a blank line before and after when there are paragraphs:

---

Preview:

Advanced Techniques

Inline HTML Elements

Currently, only some inline HTML elements are supported, including <kdb> , such as

Key Display

Use <kbd>Ctrl</kbd> + <kbd>Alt</kbd> + <kbd>Del</kbd> to reboot the computer

Preview:

Use Ctrl + Alt + Del to reboot the computer

Bold Italics

<b> Markdown also applies here, such as _bold_ </b>

Preview:

Markdown also applies here, such as bold

Other HTML Writing

Foldable Blocks

<details><summary>Click to expand</summary>It is hidden</details>

Preview:

Tables

| Header1  | Header2  |
| -------- | -------- |
| Content1 | Content2 |

Preview:

| Header1 | Header2 | | -------- | -------- | | Content1 | Content2 |

Footnotes

Use [^footnote] to add a footnote at the point of reference.

Then, at the end of the document, add the content of the footnote (it will be rendered at the end of the article by default).

[^footnote]: Here is the content of the footnote

Preview:

Use [^footnote] to add a footnote at the point of reference.

Then, at the end of the document, add the content of the footnote (it will be rendered at the end of the article by default).

[^footnote]: Here is the content of the footnote

To-Do Lists

- [ ] Incomplete task
- [x] Completed task

Preview:

[ ] Incomplete task
[x] Completed task

Symbol Escaping

If you need to use markdown symbols like _ # * in your description but don't want them to be escaped, you can add a backslash before these symbols, such as \_ \# \* to avoid it.

\_Don't want the text here to be italic\_

\*\*Don't want the text here to be bold\*\*

Preview:

_Don't want the text here to be italic_

**Don't want the text here to be bold**

Embedding Astro Components

See User Components and Advanced Components for details.