Coding Assistant on Producthunt daily

awesome-claude-code

Wed, 23 Jul 2025 15:36:28 +0800

hesreallyhim/awesome-claude-code

 █████┐ ██┐    ██┐███████┐███████┐ ██████┐ ███┐   ███┐███████┐
██┌──██┐██│    ██│██┌────┘██┌────┘██┌───██┐████┐ ████│██┌────┘
███████│██│ █┐ ██│█████┐  ███████┐██│   ██│██┌████┌██│█████┐
██┌──██│██│███┐██│██┌──┘  └────██│██│   ██│██│└██┌┘██│██┌──┘
██│  ██│└███┌███┌┘███████┐███████│└██████┌┘██│ └─┘ ██│███████┐
└─┘  └─┘ └──┘└──┘ └──────┘└──────┘ └─────┘ └─┘     └─┘└──────┘

 ────────────────────────────────────────────────────────────────────────────────────

 ██████┐██┐      █████┐ ██┐   ██┐██████┐ ███████┐     ██████┐ ██████┐ ██████┐ ███████┐
██┌────┘██│     ██┌──██┐██│   ██│██┌──██┐██┌────┘    ██┌────┘██┌───██┐██┌──██┐██┌────┘
██│     ██│     ███████│██│   ██│██│  ██│█████┐      ██│     ██│   ██│██│  ██│█████┐
██│     ██│     ██┌──██│██│   ██│██│  ██│██┌──┘      ██│     ██│   ██│██│  ██│██┌──┘
└██████┐███████┐██│  ██│└██████┌┘██████┌┘███████┐    └██████┐└██████┌┘██████┌┘███████┐
 └─────┘└──────┘└─┘  └─┘ └─────┘ └─────┘ └──────┘     └─────┘ └─────┘ └─────┘ └──────┘

This is a curated list of slash-commands, CLAUDE.md files, CLI tools, and other resources and guides for enhancing your Claude Code workflow, productivity, and vibes.

Claude Code is a cutting-edge CLI-based coding assistant and agent that you can access in your terminal or IDE. It is a rapidly evolving tool that offers a number of powerful capabilities, and allows for a lot of configuration, in a lot of different ways. Users are actively working out best practices and workflows. It is the hope that this repo will help the community share knowledge and understand how to get the most out of Claude Code.

Announcements

2025-07-18 - I ended up over-engineering the submission workflow, but I think it’s done, I just have to smoke test it and update the docs. For anyone with existing PR’s, don’t worry about updating them (for formatting purposes, that is), I can take care of it myself. For anoyne with new PR’s, you should be able to run make submit from the root directory of your fork for an interactive experience (as I said, needs smoke testing) - alternatively, add your entry to the bottom of THE_RESOURCES_TABLE and run make generate to automatically update the README.md based on the information you filled in. If it’s not working, just open a PR with the relevant information and I’ll deal with it, I created this mess anyway 😃.

▪     Workflows & Knowledge Guides
▪     Tooling
          ▫     IDE Integrations
▪     Hooks
▪     Slash-Commands
          ▫     Version Control & Git
          ▫     Code Analysis & Testing
          ▫     Context Loading & Priming
          ▫     Documentation & Changelogs
          ▫     CI / Deployment
          ▫     Project & Task Management
          ▫     Miscellaneous
▪     CLAUDE.md Files
          ▫     Language-Specific
          ▫     Domain-Specific
          ▫     Project Scaffolding & MCP
▪     Official Documentation

Workflows & Knowledge Guides 🧠

A workflow is a tightly coupled set of Claude Code-native resources that facilitate specific projects

Blogging Platform Instructions by cloudartisan ⚖️ CC-BY-SA-4.0
Provides a well-structured set of commands for publishing and maintaining a blogging platform, including commands for creating posts, managing categories, and handling media files.

ClaudeLog by InventorBlack
A comprehensive knowledge repository that features detailed breakdowns of advanced Claude Code mechanics including CLAUDE.md best practices, practical technique guides like plan mode, and a configuration guide.

Context Priming by disler
Provides a systematic approach to priming Claude Code with comprehensive project context through specialized commands for different project scenarios and development contexts.

n8n_agent by kingler
Amazing comprehensive set of comments for code analysis, QA, design, documentation, project structure, project management, optimization, and many more.

Project Bootstrapping and Task Management by steadycursor
Provides a structured set of commands for bootstrapping and managing a new project, including meta-commands for creating and editing custom slash-commands.

Project Management, Implementation, Planning, and Release by scopecraft
Really comprehensive set of commands for all aspects of SDLC.

Project Workflow System by harperreed
A set of commands that provide a comprehensive workflow system for managing projects, including task management, code review, and deployment processes.

Shipping Real Code w/ Claude by Diwank
A detailed blog post explaining the author’s process for shipping a product with Claude Code, including CLAUDE.md files and other interesting resources.

Simone by Helmi ⚖️ MIT
A broader project management workflow for Claude Code that encompasses not just a set of commands, but a system of documents, guidelines, and processes to facilitate project planning and execution.

Slash-commands megalist by wcygan
A pretty stunning list (88 at the time of this post!) of slash-commands ranging from agent orchestration, code review, project management, security, documentation, self-assessment, almost anything you can dream of.

Tooling 🧰

Tooling denotes applications that are built on top of Claude Code and consist of more components than slash-commands and CLAUDE.md files

CC Usage by ryoppippi ⚖️ MIT
Handy CLI tool for managing and analyzing Claude Code usage, based on analyzing local Claude Code logs. Presents a nice dashboard regarding cost information, token consumption, etc.

ccexp by nyatinte ⚖️ MIT
Interactive CLI tool for discovering and managing Claude Code configuration files and slash commands with a beautiful terminal UI.

Claude Code Flow by ruvnet ⚖️ MIT
This mode serves as a code-first orchestration layer, enabling Claude to write, edit, test, and optimize code autonomously across recursive agent cycles.

Claude Composer by Mike Bannister ⚖️ Unlicense
A tool that adds small enhancements to Claude Code.

Claude Hub by Claude Did This
A webhook service that connects Claude Code to GitHub repositories, enabling AI-powered code assistance directly through pull requests and issues. This integration allows Claude to analyze repositories, answer technical questions, and help developers understand and improve their codebase through simple @mentions.

Claude Squad by smtg-ai ⚖️ AGPL-3.0
Claude Squad is a terminal app that manages multiple Claude Code, Codex (and other local agents including Aider) in separate workspaces, allowing you to work on multiple tasks simultaneously.

Claude Swarm by parruda ⚖️ MIT
Launch Claude Code session that is connected to a swarm of Claude Code Agents.

Claude Task Master by eyaltoledano ⚖️ NOASSERTION
A task management system for AI-driven development with Claude, designed to work seamlessly with Cursor AI.

Claude Task Runner by grahama1970
A specialized tool to manage context isolation and focused task execution with Claude Code, solving the critical challenge of context length limitations and task focus when working with Claude on complex, multi-step projects.

Container Use by dagger ⚖️ Apache-2.0
Development environments for coding agents. Enable multiple agents to work safely and independently with your preferred stack.

IDE Integrations

claude-code.el by stevemolitor ⚖️ Apache-2.0
An Emacs interface for Claude Code CLI.

claude-code.nvim by greggh ⚖️ MIT
A seamless integration between Claude Code AI assistant and Neovim.

crystal by stravu ⚖️ MIT
A full-fledged desktop application for orchestrating, monitoring, and interacting with Claude Code agents.

Hooks 🪝

Hooks are a brand new API for Claude Code that allows users to activate commands and run scripts at different points in Claude’s agentic lifecycle.

[Experimental] - The resources listed in this section have not been fully vetted and may not work as expected, given the bleeding-edge nature of Claude Code hooks. Nevertheless, I wished to include them at least as a source of inspiration and to explore this unknown terrain. YMMV!

claude-code-hooks-sdk by beyondcode ⚖️ MIT
A Laravel-inspired PHP SDK for building Claude Code hook responses with a clean, fluent API. This SDK makes it easy to create structured JSON responses for Claude Code hooks using an expressive, chainable interface.

claude-hooks by John Lindquist ⚖️ MIT
A TypeScript-based system for configuring and customizing Claude Code hooks with a powerful and flexible interface.

Linting, testing, and notifications (in go) by Josh Symonds ⚖️ MIT
Nice set of hooks for enforcing code quality (linting, testing, notifications), with a nice configuration setup as well.

TDD Guard by Nizar Selander ⚖️ MIT
A hooks-driven system that monitors file operations in real-time and blocks changes that violate TDD principles.

Slash-Commands 🔪

Version Control & Git

/bug-fix by danielscholl
Streamlines bug fixing by creating a GitHub issue first, then a feature branch for implementing and thoroughly testing the solution before merging.

/commit by evmts ⚖️ MIT
Creates git commits using conventional commit format with appropriate emojis, following project standards and creating descriptive messages that explain the purpose of changes.

/commit-fast by steadycursor
Automates git commit process by selecting the first suggested message, generating structured commits with consistent formatting while skipping manual confirmation and removing Claude co-Contributorship footer

/create-pr by toyamarinyon ⚖️ Apache-2.0
Streamlines pull request creation by handling the entire workflow: creating a new branch, committing changes, formatting modified files with Biome, and submitting the PR.

/create-pull-request by liam-hq ⚖️ Apache-2.0
Provides comprehensive PR creation guidance with GitHub CLI, enforcing title conventions, following template structure, and offering concrete command examples with best practices.

/create-worktrees by evmts ⚖️ MIT
Creates git worktrees for all open PRs or specific branches, handling branches with slashes, cleaning up stale worktrees, and supporting custom branch creation for development.

/fix-github-issue by jeremymailen ⚖️ Apache-2.0
Analyzes and fixes GitHub issues using a structured approach with GitHub CLI for issue details, implementing necessary code changes, running tests, and creating proper commit messages.

/fix-issue by metabase ⚖️ NOASSERTION
Addresses GitHub issues by taking issue number as parameter, analyzing context, implementing solution, and testing/validating the fix for proper integration.

/fix-pr by metabase ⚖️ NOASSERTION
Fetches and fixes unresolved PR comments by automatically retrieving feedback, addressing reviewer concerns, making targeted code improvements, and streamlining the review process.

/husky by evmts ⚖️ MIT
Sets up and manages Husky Git hooks by configuring pre-commit hooks, establishing commit message standards, integrating with linting tools, and ensuring code quality on commits.

/pr-review by arkavo-org ⚖️ MIT
Reviews pull request changes to provide feedback, check for issues, and suggest improvements before merging into the main codebase.

/update-branch-name by giselles-ai ⚖️ Apache-2.0
Updates branch names with proper prefixes and formats, enforcing naming conventions, supporting semantic prefixes, and managing remote branch updates.

Code Analysis & Testing

/check by rygwdn
Performs comprehensive code quality and security checks, featuring static analysis integration, security vulnerability scanning, code style enforcement, and detailed reporting.

/clean by Graphlet-AI ⚖️ Apache-2.0
Addresses code formatting and quality issues by fixing black formatting problems, organizing imports with isort, resolving flake8 linting issues, and correcting mypy type errors.

/code_analysis by kingler
Provides a menu of advanced code analysis commands for deep inspection, including knowledge graph generation, optimization suggestions, and quality evaluation.

/optimize by to4iki ⚖️ MIT
Analyzes code performance to identify bottlenecks, proposing concrete optimizations with implementation guidance for improved application performance.

/repro-issue by rzykov ⚖️ NOASSERTION
Creates reproducible test cases for GitHub issues, ensuring tests fail reliably and documenting clear reproduction steps for developers.

/tdd by zscott
Guides development using Test-Driven Development principles, enforcing Red-Green-Refactor discipline, integrating with git workflow, and managing PR creation.

Context Loading & Priming

/context-prime by elizaOS ⚖️ MIT
Primes Claude with comprehensive project understanding by loading repository structure, setting development context, establishing project goals, and defining collaboration parameters.

/initref by okuvshynov ⚖️ MIT
Initializes reference documentation structure with standard doc templates, API reference setup, documentation conventions, and placeholder content generation.

/load-llms-txt by ethpandaops ⚖️ MIT
Loads LLM configuration files to context, importing specific terminology, model configurations, and establishing baseline terminology for AI discussions.

/load_coo_context by Mjvolk3
References specific files for sparse matrix operations, explains transform usage, compares with previous approaches, and sets data formatting context for development.

/load_dango_pipeline by Mjvolk3
Sets context for model training by referencing pipeline files, establishing working context, and preparing for pipeline work with relevant documentation.

/prime by yzyydev
Sets up initial project context by viewing directory structure and reading key files, creating standardized context with directory visualization and key documentation focus.

/rsi by ddisisto
Reads all commands and key project files to optimize AI-assisted development by streamlining the process, loading command context, and setting up for better development workflow.

Documentation & Changelogs

/add-to-changelog by berrydev-ai ⚖️ MIT
Adds new entries to changelog files while maintaining format consistency, properly documenting changes, and following established project standards for version tracking.

/create-docs by jerseycheese ⚖️ MIT
Analyzes code structure and purpose to create comprehensive documentation detailing inputs/outputs, behavior, user interaction flows, and edge cases with error handling.

/docs by slunsford
Generates comprehensive documentation that follows project structure, documenting APIs and usage patterns with consistent formatting for better user understanding.

/explain-issue-fix by hackdays-io
Documents solution approaches for GitHub issues, explaining technical decisions, detailing challenges overcome, and providing implementation context for better understanding.

/update-docs by Consiliency ⚖️ MIT
Reviews current documentation status, updates implementation progress, reviews phase documents, and maintains documentation consistency across the project.

CI / Deployment

/release by kelp ⚖️ MIT
Manages software releases by updating changelogs, reviewing README changes, evaluating version increments, and documenting release changes for better version tracking.

/run-ci by hackdays-io
Activates virtual environments, runs CI-compatible check scripts, iteratively fixes errors, and ensures all tests pass before completion.

Project & Task Management

/create-command by scopecraft
Guides Claude through creating new custom commands with proper structure by analyzing requirements, templating commands by category, enforcing command standards, and creating supporting documentation.

/create-jtbd by taddyorg ⚖️ AGPL-3.0
Creates Jobs-to-be-Done frameworks that outline user needs with structured format, focusing on specific user problems and organizing by job categories for product development.

/create-prd by taddyorg ⚖️ AGPL-3.0
Generates comprehensive product requirement documents outlining detailed specifications, requirements, and features following standardized document structure and format.

/create-prp by Wirasm ⚖️ MIT
Creates product requirement plans by reading PRP methodology, following template structure, creating comprehensive requirements, and structuring product definitions for development.

/project_hello_w_name by disler
Creates customizable greeting components with name input, demonstrating argument passing, component reusability, state management, and user input handling.

/todo by chrisleyva ⚖️ MIT
A convenient command to quickly manage project todo items without leaving the Claude Code interface, featuring due dates, sorting, task prioritization, and comprehensive todo list management.

Miscellaneous

/five by TuckerTucker
Applies the “five whys” methodology to perform root cause analysis, identify underlying issues, and create solution approaches for complex problems.

/fixing_go_in_graph by Mjvolk3
Focuses on Gene Ontology annotation integration in graph databases, handling multiple data sources, addressing graph representation issues, and ensuring correct data incorporation.

/mermaid by GaloyMoney ⚖️ NOASSERTION
Generates Mermaid diagrams from SQL schema files, creating entity relationship diagrams with table properties, validating diagram compilation, and ensuring complete entity coverage.

/review_dcell_model by Mjvolk3
Reviews old Dcell implementation files, comparing with newer Dango model, noting changes over time, and analyzing refactoring approaches for better code organization.

/use-stepper by zuplo
Reformats documentation to use React Stepper component, transforming heading formats, applying proper indentation, and maintaining markdown compatibility with admonition formatting.

CLAUDE.md Files 📂

CLAUDE.md files are files that contain important guidelines and context-specfic information or instructions that help Claude Code to better understand your project and your coding standards

Language-Specific

AI IntelliJ Plugin by didalgolab ⚖️ Apache-2.0
Provides comprehensive Gradle commands for IntelliJ plugin development with platform-specific coding patterns, detailed package structure guidelines, and clear internationalization standards.

AWS MCP Server by alexei-led ⚖️ MIT
Features multiple Python environment setup options with detailed code style guidelines, comprehensive error handling recommendations, and security considerations for AWS CLI interactions.

DroidconKotlin by touchlab ⚖️ Apache-2.0
Delivers comprehensive Gradle commands for cross-platform Kotlin Multiplatform development with clear module structure and practical guidance for dependency injection.

EDSL by expectedparrot ⚖️ MIT
Offers detailed build and test commands with strict code style enforcement, comprehensive testing requirements, and standardized development workflow using Black and mypy.

Giselle by giselles-ai ⚖️ Apache-2.0
Provides detailed build and test commands using pnpm and Vitest with strict code formatting requirements and comprehensive naming conventions for code consistency.

HASH by hashintel ⚖️ NOASSERTION
Features comprehensive repository structure breakdown with strong emphasis on coding standards, detailed Rust documentation guidelines, and systematic PR review process.

Inkline by inkline ⚖️ NOASSERTION
Structures development workflow using pnpm with emphasis on TypeScript and Vue 3 Composition API, detailed component creation process, and comprehensive testing recommendations.

JSBeeb by mattgodbolt ⚖️ GPL-3.0
Provides development guide for JavaScript BBC Micro emulator with build and testing instructions, architecture documentation, and debugging workflows.

Lamoom Python by LamoomAI ⚖️ Apache-2.0
Serves as reference for production prompt engineering library with load balancing of AI Models, API documentation, and usage patterns with examples.

LangGraphJS by langchain-ai ⚖️ MIT
Offers comprehensive build and test commands with detailed TypeScript style guidelines, layered library architecture, and monorepo structure using yarn workspaces.

Metabase by metabase ⚖️ NOASSERTION
Details workflow for REPL-driven development in Clojure/ClojureScript with emphasis on incremental development, testing, and step-by-step approach for feature implementation.

SG Cars Trends Backend by sgcarstrends
Provides comprehensive structure for TypeScript monorepo projects with detailed commands for development, testing, deployment, and AWS/Cloudflare integration.

SPy by spylang ⚖️ MIT
Enforces strict coding conventions with comprehensive testing guidelines, multiple code compilation options, and backend-specific test decorators for targeted filtering.

TPL by KarpelesLab ⚖️ MIT
Details Go project conventions with comprehensive error handling recommendations, table-driven testing approach guidelines, and modernization suggestions for latest Go features.

Domain-Specific

AVS Vibe Developer Guide by Layr-Labs ⚖️ MIT
Structures AI-assisted EigenLayer AVS development workflow with consistent naming conventions for prompt files and established terminology standards for blockchain concepts.

Comm by CommE2E ⚖️ BSD-3-Clause
Serves as a development reference for E2E-encrypted messaging applications with code organization architecture, security implementation details, and testing procedures.

Course Builder by badass-courses ⚖️ MIT
Enables real-time multiplayer capabilities for collaborative course creation with diverse tech stack integration and monorepo architecture using Turborepo.

Cursor Tools by eastlondoner ⚖️ MIT
Creates a versatile AI command interface supporting multiple providers and models with flexible command options and browser automation through “Stagehand” feature.

Guitar by soramimi ⚖️ GPL-2.0
Serves as development guide for Guitar Git GUI Client with build commands for various platforms, code style guidelines for contributing, and project structure explanation.

Network Chronicles by Fimeg ⚖️ MIT
Presents detailed implementation plan for AI-driven game characters with technical specifications for LLM integration, character guidelines, and service discovery mechanics.

Note Companion by different-ai ⚖️ MIT
Provides detailed styling isolation techniques for Obsidian plugins using Tailwind with custom prefix to prevent style conflicts and practical troubleshooting steps.

Pareto Mac by ParetoSecurity ⚖️ GPL-3.0
Serves as development guide for Mac security audit tool with build instructions, contribution guidelines, testing procedures, and workflow documentation.

SteadyStart by steadycursor
Clear and direct instructives about style, permissions, Claude’s “role”, communications, and documentation of Claude Code sessions for other team members to stay abreast.

Project Scaffolding & MCP

Basic Memory by basicmachines-co ⚖️ AGPL-3.0
Presents an innovative AI-human collaboration framework with Model Context Protocol for bidirectional LLM-markdown communication and flexible knowledge structure for complex projects.

claude-code-mcp-enhanced by grahama1970 ⚖️ MIT
Provides detailed and emphatic instructions for Claude to follow as a coding agent, with testing guidance, code examples, and compliance checks.

Perplexity MCP by Family-IT-Guy ⚖️ ISC
Offers clear step-by-step installation instructions with multiple configuration options, detailed troubleshooting guidance, and concise architecture overview of the MCP protocol.

Official Documentation 🏛️

Links to some of Anthropic’s terrific documentation and resources regarding Claude Code

Anthropic Documentation by Anthropic ⚖️ ©
The official documentation for Claude Code, including installation instructions, usage guidelines, API references, tutorials, examples, loads of information that I won’t list individually. Like Claude Code, the documentation is frequently updated.

Anthropic Quickstarts by Anthropic ⚖️ MIT
Offers comprehensive development guides for three distinct AI-powered demo projects with standardized workflows, strict code style guidelines, and containerization instructions.

Contributing 🌻

Please note that this project is released with a Contributor Code of Conduct. By participating in this project you agree to abide by its terms.

Regarding content, we especially welcome:

Proven, effective resources that follow best practices and may even be in use in production.
Innovative, creative, or experimental workflows that perhaps are still being iterated upon, but have high potential value, and push the boundaries of Claude Code’s documented capabilities and use cases.
Additional libraries and tooling that are built on top of Claude Code and offer enhanced functionality.
Applications of Claude Code outside of the traditional “coding assistant” context, e.g., CI/CD integration, testing, documentation, dev-ops, etc.

See CONTRIBUTING.md for more information on how to contribute to this project. Or, fire up Claude Code and invoke the /project:add-new-resource command and let Claude walk you through it!

If you have any suggestions or thoughts on how to improve the repo, or how to best organize the list, feel free to start a Discussion topic. This is meant to be for the Claude Code community, and in general I prefer not to act on sole authority.

A note about licenses

Because simply listing a hyperlink does not qualify as redistribution, the license of the original source is not relevant to its inclusion. However, for posterity and convenience, we do host copies of all resources whose license permits it. Therefore, please include information about the resource’s license. Additionally, take note: if you do not include a LICENSE in your GitHub repo, then by default it is fully copyrighted and redistribution is not allowed. So, if you are intending to make an open source project, it’s critical to pick from one of the many available open source licenses. This is just a reminder that without a LICENSE, your project is not open source (it’s merely source-code-available) - it may of course still be included on this list, but this notice is to inform readers about the default rules regarding GitHub and LICENSE files. See here for more details.

Mastering-GitHub-Copilot-for-Paired-Programming

Thu, 03 Jul 2025 15:29:41 +0800

microsoft/Mastering-GitHub-Copilot-for-Paired-Programming

Mastering GitHub Copilot

Unlock the next generation of collaborative coding with our newly updated, in-depth course: Mastering GitHub Copilot. This multi-module, 10-hour program now features GitHub Copilot’s revolutionary Agent Mode, transforming Copilot from a passive assistant into a proactive AI coding partner that works with you—and for you.

Whether you’re just starting out or an experienced developer, this course equips you to fully harness GitHub Copilot’s AI capabilities, including real-time autonomous code execution, intelligent problem-solving, and workflow automation. You’ll learn how to collaborate with AI using natural-language prompts that initiate multi-step solutions—from initial planning and architecture suggestions to code generation, testing, and iteration.

🌱 Getting Started

To get started, make sure to follow the instructions on how to fork the lessons into your own GitHub account. This will allow you to modify the code and complete the challenges at your own pace.

To use GitHub Copilot, you must have an active GitHub Copilot subscription.

Sign up for free here: GitHub Copilot.

To make it easier to revisit this repository in the future, you can also star (🌟) this repo this repo.

Below are links to each lesson—feel free to explore and dive into any topic that interests you the most!

🧠 Want to learn more?

After completing this course, check out our GitHub Copilot Learn Collection to continue leveling up your AI Peer Programming knowledge!

🚀 Are you a startup or got an idea you want to launch?

Sign up for Microsoft for Startups Founders Hub to receive free OpenAI credits and up to $150k towards Azure credits to access OpenAI models through Azure OpenAI Services.

🙏 Want to help?

Here are ways you can contribute to this course:

Find spelling errors or code errors, Raise an issue or Create a pull request
Send us your ideas, maybe your ideas for new lessons or exercises, and let us know how we can improve.

📂 Each lesson includes:

a written lesson located in the README
a challenge or assignment to apply your learning
links to extra resources to continue your learning

🗃️ Lessons

Beginner

Lesson Link	Concepts Taught	Learning Goal
Getting Started with GitHub Copilot	GitHub Copilot is an AI coding assistant that can help you write code faster and with less effort, allowing you to focus more energy on problem solving and collaboration.	In this exercise, you’ll unlock the potential of this AI-powered coding assistant to accelerate your development process.

Intermediate

Lesson Link	Concepts Taught	Learning Goal
Using GitHub Copilot with JavaScript	Use GitHub Copilot, an AI pair programmer that offers autocomplete-style suggestions as you code, to work with JavaScript.	Enable the GitHub Copilot extension in Visual Studio Code. Craft prompts that can generate useful suggestions from GitHub Copilot. Use GitHub Copilot to improve a JavaScript project.
Using GitHub Copilot with Python	Use GitHub Copilot, an AI pair programmer that offers autocomplete-style suggestions as you code, to work with Python.	Enable the GitHub Copilot extension in Visual Studio Code. Craft prompts that can generate useful suggestions from GitHub Copilot. Use GitHub Copilot to improve a Python project.
Using GitHub Copilot with C#	Use GitHub Copilot, an AI pair programmer that offers autocomplete-style suggestions as you code, to work with C#.	Enable the GitHub Copilot extension in Visual Studio Code. Craft prompts that can generate useful suggestions from GitHub Copilot. Use GitHub Copilot to improve a C# Minimal API project.
Creating a Mini Game with GitHub Copilot	Use GitHub Copilot to assist you in building a Python-based mini game.	Craft prompts that can generate useful suggestions from GitHub Copilot to incorporate gaming logic and improve your Python-based game.

Advanced

Lesson Link	Concepts Taught	Learning Goal
Using Advanced GitHub Copilot Features	Use advanced GitHub Copilot features like inline chat, slash commands, and agents.	Interact with GitHub Copilot with deeper context on your project and ask questions about it.
Getting Started with Copilot for Azure to Deploy to the Cloud	Learn cloud deployment with GitHub Copilot for Azure—your ultimate guide to streamlined cloud success.	Effortless application deployment leveraging Azure’s powerful scalability.
NEW Challenging GitHub Copilot with complex SQL	Apply advanced GitHub Copilot features to work with a challenging application working with a complex SQL query	Gain a clear understanding of how to work with extremely challenging SQL and yield better results when simple prompts don’t work well
NEW Upgrading Legacy project	Leverage GitHub Copilot to upgrade a legacy Python project to the latest version of Python.	Apply techniques to overcome the challenges involved in working with legacy projects
NEW Migrating to a new language	Rewrite an existing application using a different language with the guidance of GitHub Copilot	Use advanced workflows with GitHub Copilot applicable when translating projects to different programming languages

🎒 Other Courses

Our team produces other courses! Check out:

agenticSeek

Sat, 31 May 2025 15:27:51 +0800

Fosowl/agenticSeek

AgenticSeek: Private, Local Manus Alternative.

A 100% local alternative to Manus AI, this voice-enabled AI assistant autonomously browses the web, writes code, and plans tasks while keeping all data on your device. Tailored for local reasoning models, it runs entirely on your hardware, ensuring complete privacy and zero cloud dependency.

Why AgenticSeek ?

🔒 Fully Local & Private - Everything runs on your machine — no cloud, no data sharing. Your files, conversations, and searches stay private.
🌐 Smart Web Browsing - AgenticSeek can browse the internet by itself — search, read, extract info, fill web form — all hands-free.
💻 Autonomous Coding Assistant - Need code? It can write, debug, and run programs in Python, C, Go, Java, and more — all without supervision.
🧠 Smart Agent Selection - You ask, it figures out the best agent for the job automatically. Like having a team of experts ready to help.
📋 Plans & Executes Complex Tasks - From trip planning to complex projects — it can split big tasks into steps and get things done using multiple AI agents.
🎙️ Voice-Enabled - Clean, fast, futuristic voice and speech to text allowing you to talk to it like it’s your personal AI from a sci-fi movie

Demo

Can you search for the agenticSeek project, learn what skills are required, then open the CV_candidates.zip and then tell me which match best the project

https://github.com/user-attachments/assets/b8ca60e9-7b3b-4533-840e-08f9ac426316

Disclaimer: This demo, including all the files that appear (e.g: CV_candidates.zip), are entirely fictional. We are not a corporation, we seek open-source contributors not candidates.

🛠⚠️️ Active Work in Progress – Please note that Code/Bash is not dockerized yet but will be soon (see docker_deployement branch) - Do not deploy over network or production.

🙏 This project started as a side-project with zero roadmap and zero funding. It’s grown way beyond what I expected by ending in GitHub Trending. Contributions, feedback, and patience are deeply appreciated.

Installation

Make sure you have chrome driver, docker and python3.10 installed.

We highly advice you use exactly python3.10 for the setup. Dependencies error might happen otherwise.

For issues related to chrome driver, see the Chromedriver section.

1️⃣ Clone the repository and setup

1
2
3

git clone https://github.com/Fosowl/agenticSeek.git
cd agenticSeek
mv .env.example .env

2️ Create a virtual env

1
2
3

python3 -m venv agentic_seek_env
source agentic_seek_env/bin/activate
# On Windows: agentic_seek_env\Scripts\activate

3️⃣ Install package

Ensure Python, Docker and docker compose, and Google chrome are installed.

We recommand Python 3.10.0.

Automatic Installation (Recommanded):

For Linux/Macos:

`1`	`./install.sh`

For windows:

`1`	`./install.bat`

Manually:

Note: For any OS, ensure the ChromeDriver you install matches your installed Chrome version. Run google-chrome --version. See known issues if you have chrome >135

Linux:

Update Package List: sudo apt update

Install Dependencies: sudo apt install -y alsa-utils portaudio19-dev python3-pyaudio libgtk-3-dev libnotify-dev libgconf-2-4 libnss3 libxss1

Install ChromeDriver matching your Chrome browser version: sudo apt install -y chromium-chromedriver

Install requirements: pip3 install -r requirements.txt

Macos:

Update brew : brew update

Install chromedriver : brew install --cask chromedriver

Install portaudio: brew install portaudio

Upgrade pip : python3 -m pip install --upgrade pip

Upgrade wheel : : pip3 install --upgrade setuptools wheel

Install requirements: pip3 install -r requirements.txt

Windows:

Install pyreadline3 pip install pyreadline3

Install portaudio manually (e.g., via vcpkg or prebuilt binaries) and then run: pip install pyaudio

Download and install chromedriver manually from: https://sites.google.com/chromium.org/driver/getting-started

Place chromedriver in a directory included in your PATH.

Install requirements: pip3 install -r requirements.txt

Setup for running LLM locally on your machine

Hardware Requirements:

To run LLMs locally, you’ll need sufficient hardware. At a minimum, a GPU capable of running Qwen/Deepseek 14B is required. See the FAQ for detailed model/performance recommendations.

Setup your local provider

Start your local provider, for example with ollama:

`1`	`ollama serve`

See below for a list of local supported provider.

Update the config.ini

Change the config.ini file to set the provider_name to a supported provider and provider_model to a LLM supported by your provider. We recommand reasoning model such as Qwen or Deepseek.

See the FAQ at the end of the README for required hardware.

[MAIN]
is_local = True # Whenever you are running locally or with remote provider.
provider_name = ollama # or lm-studio, openai, etc..
provider_model = deepseek-r1:14b # choose a model that fit your hardware
provider_server_address = 127.0.0.1:11434
agent_name = Jarvis # name of your AI
recover_last_session = True # whenever to recover the previous session
save_session = True # whenever to remember the current session
speak = True # text to speech
listen = False # Speech to text, only for CLI
work_dir =  /Users/mlg/Documents/workspace # The workspace for AgenticSeek.
jarvis_personality = False # Whenever to use a more "Jarvis" like personality (experimental)
languages = en zh # The list of languages, Text to speech will default to the first language on the list
[BROWSER]
headless_browser = True # Whenever to use headless browser, recommanded only if you use web interface.
stealth_mode = True # Use undetected selenium to reduce browser detection

Warning: Do NOT set provider_name to openai if using LM-studio for running LLMs. Set it to lm-studio.

Note: Some provider (eg: lm-studio) require you to have http:// in front of the IP. For example http://127.0.0.1:1234

List of local providers

Provider	Local?	Description
ollama	Yes	Run LLMs locally with ease using ollama as a LLM provider
lm-studio	Yes	Run LLM locally with LM studio (set `provider_name` to `lm-studio`)
openai	Yes	Use openai compatible API (eg: llama.cpp server)

Next step: Start services and run AgenticSeek

See the Known issues section if you are having issues

See the Run with an API section if your hardware can’t run deepseek locally

See the Config section for detailled config file explanation.

Setup to run with an API

Set the desired provider in the config.ini. See below for a list of API providers.

[MAIN]
is_local = False
provider_name = google
provider_model = gemini-2.0-flash
provider_server_address = 127.0.0.1:5000 # doesn't matter

Warning: Make sure there is not trailing space in the config.

Export your API key: export <<PROVIDER>>_API_KEY="xxx"

Example: export TOGETHER_API_KEY="xxxxx"

List of API providers

Provider	Local?	Description
openai	Depends	Use ChatGPT API
deepseek	No	Deepseek API (non-private)
huggingface	No	Hugging-Face API (non-private)
togetherAI	No	Use together AI API (non-private)
google	No	Use google gemini API (non-private)

We advice against using gpt-4o or other closedAI models, performance are poor for web browsing and task planning.

Please also note that coding/bash might fail with gemini, it seem to ignore our prompt for format to respect, which are optimized for deepseek r1.

Next step: Start services and run AgenticSeek

See the Known issues section if you are having issues

See the Config section for detailled config file explanation.

Start services and Run

Activate your python env if needed.

`1`	`source agentic_seek_env/bin/activate`

Start required services. This will start all services from the docker-compose.yml, including: - searxng - redis (required by searxng) - frontend

1
2

sudo ./start_services.sh # MacOS
start ./start_services.cmd # Window

Options 1: Run with the CLI interface.

`1`	`python3 cli.py`

We advice you set headless_browser to False in the config.ini for CLI mode.

Options 2: Run with the Web interface.

Start the backend.

`1`	`python3 api.py`

Go to http://localhost:3000/ and you should see the web interface.

Usage

Make sure the services are up and running with ./start_services.sh and run the AgenticSeek with python3 cli.py for CLI mode or python3 api.py then go to localhost:3000 for web interface.

You can also use speech to text by setting listen = True in the config. Only for CLI mode.

To exit, simply say/type goodbye.

Here are some example usage:

Make a snake game in python!

Search the web for top cafes in Rennes, France, and save a list of three with their addresses in rennes_cafes.txt.

Write a Go program to calculate the factorial of a number, save it as factorial.go in your workspace

Search my summer_pictures folder for all JPG files, rename them with today’s date, and save a list of renamed files in photos_list.txt

Search online for popular sci-fi movies from 2024 and pick three to watch tonight. Save the list in movie_night.txt.

Search the web for the latest AI news articles from 2025, select three, and write a Python script to scrape their titles and summaries. Save the script as news_scraper.py and the summaries in ai_news.txt in /home/projects

Friday, search the web for a free stock price API, register with supersuper7434567@gmail.com then write a Python script to fetch using the API daily prices for Tesla, and save the results in stock_prices.csv

Note that form filling capabilities are still experimental and might fail.

After you type your query, AgenticSeek will allocate the best agent for the task.

Because this is an early prototype, the agent routing system might not always allocate the right agent based on your query.

Therefore, you should be very explicit in what you want and how the AI might proceed for example if you want it to conduct a web search, do not say:

Do you know some good countries for solo-travel?

Instead, ask:

Do a web search and find out which are the best country for solo-travel

Setup to run the LLM on your own server

If you have a powerful computer or a server that you can use, but you want to use it from your laptop you have the options to run the LLM on a remote server using our custom llm server.

On your “server” that will run the AI model, get the ip address

1
2

ip a | grep "inet " | grep -v 127.0.0.1 | awk '{print $2}' | cut -d/ -f1 # local ip
curl https://ipinfo.io/ip # public ip

Note: For Windows or macOS, use ipconfig or ifconfig respectively to find the IP address.

Clone the repository and enter the server/folder.

1
2

git clone --depth 1 https://github.com/Fosowl/agenticSeek.git
cd agenticSeek/llm_server/

Install server specific requirements:

`1`	`pip3 install -r requirements.txt`

Run the server script.

`1`	`python3 app.py --provider ollama --port 3333`

You have the choice between using ollama and llamacpp as a LLM service.

Now on your personal computer:

Change the config.ini file to set the provider_name to server and provider_model to deepseek-r1:xxb. Set the provider_server_address to the ip address of the machine that will run the model.

[MAIN]
is_local = False
provider_name = server
provider_model = deepseek-r1:70b
provider_server_address = x.x.x.x:3333

Next step: Start services and run AgenticSeek

Speech to Text

Please note that currently speech to text only work in english.

The speech-to-text functionality is disabled by default. To enable it, set the listen option to True in the config.ini file:

`1`	`listen = True`

When enabled, the speech-to-text feature listens for a trigger keyword, which is the agent’s name, before it begins processing your input. You can customize the agent’s name by updating the agent_name value in the config.ini file:

`1`	`agent_name = Friday`

For optimal recognition, we recommend using a common English name like “John” or “Emma” as the agent name

Once you see the transcript start to appear, say the agent’s name aloud to wake it up (e.g., “Friday”).

Speak your query clearly.

End your request with a confirmation phrase to signal the system to proceed. Examples of confirmation phrases include:

`1`	`"do it", "go ahead", "execute", "run", "start", "thanks", "would ya", "please", "okay?", "proceed", "continue", "go on", "do that", "go it", "do you understand?"`

Config

Example config:

[MAIN]
is_local = True
provider_name = ollama
provider_model = deepseek-r1:32b
provider_server_address = 127.0.0.1:11434
agent_name = Friday
recover_last_session = False
save_session = False
speak = False
listen = False
work_dir =  /Users/mlg/Documents/ai_folder
jarvis_personality = False
languages = en zh
[BROWSER]
headless_browser = False
stealth_mode = False

Explanation:

is_local -> Runs the agent locally (True) or on a remote server (False).
provider_name -> The provider to use (one of: ollama, server, lm-studio, deepseek-api)
provider_model -> The model used, e.g., deepseek-r1:32b.
provider_server_address -> Server address, e.g., 127.0.0.1:11434 for local. Set to anything for non-local API.
agent_name -> Name of the agent, e.g., Friday. Used as a trigger word for TTS.
recover_last_session -> Restarts from last session (True) or not (False).
save_session -> Saves session data (True) or not (False).
speak -> Enables voice output (True) or not (False).
listen -> listen to voice input (True) or not (False).
work_dir -> Folder the AI will have access to. eg: /Users/user/Documents/.
jarvis_personality -> Uses a JARVIS-like personality (True) or not (False). This simply change the prompt file.
languages -> The list of supported language, needed for the llm router to work properly, avoid putting too many or too similar languages.
headless_browser -> Runs browser without a visible window (True) or not (False).
stealth_mode -> Make bot detector time harder. Only downside is you have to manually install the anticaptcha extension.
languages -> List of supported languages. Required for agent routing system. The longer the languages list the more model will be downloaded.

Providers

The table below show the available providers:

Provider	Local?	Description
ollama	Yes	Run LLMs locally with ease using ollama as a LLM provider
server	Yes	Host the model on another machine, run your local machine
lm-studio	Yes	Run LLM locally with LM studio (`lm-studio`)
openai	Depends	Use ChatGPT API (non-private) or openai compatible API
deepseek-api	No	Deepseek API (non-private)
huggingface	No	Hugging-Face API (non-private)
togetherAI	No	Use together AI API (non-private)
google	No	Use google gemini API (non-private)

To select a provider change the config.ini:

is_local = True
provider_name = ollama
provider_model = deepseek-r1:32b
provider_server_address = 127.0.0.1:5000

is_local: should be True for any locally running LLM, otherwise False.

provider_name: Select the provider to use by it’s name, see the provider list above.

provider_model: Set the model to use by the agent.

provider_server_address: can be set to anything if you are not using the server provider.

Known issues

Chromedriver Issues

Known error #1: chromedriver mismatch

Exception: Failed to initialize browser: Message: session not created: This version of ChromeDriver only supports Chrome version 113 Current browser version is 134.0.6998.89 with binary path

This happen if there is a mismatch between your browser and chromedriver version.

You need to navigate to download the latest version:

https://developer.chrome.com/docs/chromedriver/downloads

If you’re using Chrome version 115 or newer go to:

https://googlechromelabs.github.io/chrome-for-testing/

And download the chromedriver version matching your OS.

If this section is incomplete please raise an issue.

connection adapters Issues

`1`	`Exception: Provider lm-studio failed: HTTP request failed: No connection adapters were found for '127.0.0.1:11434/v1/chat/completions'`

Make sure you have http:// in front of the provider IP address :

provider_server_address = http://127.0.0.1:11434

SearxNG base URL must be provided

1
2

raise ValueError("SearxNG base URL must be provided either as an argument or via the SEARXNG_BASE_URL environment variable.")
ValueError: SearxNG base URL must be provided either as an argument or via the SEARXNG_BASE_URL environment variable.

Maybe you didn’t move .env.example as .env ? You can also export SEARXNG_BASE_URL:

export SEARXNG_BASE_URL="http://127.0.0.1:8080"

FAQ

Q: What hardware do I need?

Model Size	GPU	Comment
7B	8GB Vram	⚠️ Not recommended. Performance is poor, frequent hallucinations, and planner agents will likely fail.
14B	12 GB VRAM (e.g. RTX 3060)	✅ Usable for simple tasks. May struggle with web browsing and planning tasks.
32B	24+ GB VRAM (e.g. RTX 4090)	🚀 Success with most tasks, might still struggle with task planning
70B+	48+ GB Vram (eg. mac studio)	💪 Excellent. Recommended for advanced use cases.

Q: Why Deepseek R1 over other models?

Deepseek R1 excels at reasoning and tool use for its size. We think it’s a solid fit for our needs other models work fine, but Deepseek is our primary pick.

Q: I get an error running cli.py. What do I do?

Ensure local is running (ollama serve), your config.ini matches your provider, and dependencies are installed. If none work feel free to raise an issue.

Q: Can it really run 100% locally?

Yes with Ollama, lm-studio or server providers, all speech to text, LLM and text to speech model run locally. Non-local options (OpenAI or others API) are optional.

Q: Why should I use AgenticSeek when I have Manus?

This started as Side-Project we did out of interest about AI agents. What’s special about it is that we want to use local model and avoid APIs. We draw inspiration from Jarvis and Friday (Iron man movies) to make it “cool” but for functionnality we take more inspiration from Manus, because that’s what people want in the first place: a local manus alternative. Unlike Manus, AgenticSeek prioritizes independence from external systems, giving you more control, privacy and avoid api cost.

Contribute

We’re looking for developers to improve AgenticSeek! Check out open issues or discussion.

Contribution guide

Maintainers:

Fosowl | Paris Time

antoineVIVIES | Taipei Time

steveh8758 | Taipei Time

Coding Assistant on Producthunt daily

awesome-claude-code

hesreallyhim/awesome-claude-code

Announcements

Contents

Workflows & Knowledge Guides 🧠

Tooling 🧰

IDE Integrations

Hooks 🪝

Slash-Commands 🔪

Version Control & Git

Code Analysis & Testing

Context Loading & Priming

Documentation & Changelogs

CI / Deployment

Project & Task Management

Miscellaneous

CLAUDE.md Files 📂

Language-Specific

Domain-Specific

Project Scaffolding & MCP

Official Documentation 🏛️

Contributing 🌻

A note about licenses

Mastering-GitHub-Copilot-for-Paired-Programming

microsoft/Mastering-GitHub-Copilot-for-Paired-Programming

Mastering GitHub Copilot

🌱 Getting Started

🧠 Want to learn more?

🚀 Are you a startup or got an idea you want to launch?

🙏 Want to help?

📂 Each lesson includes:

🗃️ Lessons

Beginner

Intermediate

Advanced

🎒 Other Courses

agenticSeek

Fosowl/agenticSeek

AgenticSeek: Private, Local Manus Alternative.

Why AgenticSeek ?

Demo

Installation

1️⃣ Clone the repository and setup

2️ Create a virtual env

3️⃣ Install package

Setup for running LLM locally on your machine

Setup to run with an API

Start services and Run

Usage

Setup to run the LLM on your own server

Speech to Text

Config

Providers

Known issues

Chromedriver Issues

connection adapters Issues

SearxNG base URL must be provided

FAQ

Contribute

Maintainers: