Open Source AI Projects
Discover 314 open source AI repositories from GitHub, each with an analysis of what it does, key features, use cases and alternatives. AI projects here are most often combined with Python, LLM and TypeScript. Last updated October 3, 2026.
314 repositories · updated October 3, 2026
agent-plugins: A Marketplace for AI Coding Assistant Skills
agent-plugins is a tool-neutral marketplace offering ready-to-install bundles that enhance AI coding assistants. It provides curated skills, tool connections, and specialist roles for developers using VS Code, GitHub Copilot CLI, or Claude Code. This repository simplifies the process of integrating advanced AI capabilities into your development workflow.
opencode-worktree: Zero-Friction Git Worktrees for AI-Driven Development
opencode-worktree is an OpenCode plugin designed to streamline git worktree management. It automates the creation and deletion of isolated development environments, complete with terminal spawning and file synchronization. This tool is ideal for AI-driven workflows, offering a zero-friction experience for developers who prioritize automation and efficiency.
Ralph Orchestrator, An Advanced Framework for Autonomous AI Agent Orchestration
Ralph Orchestrator is a robust, Rust-based framework designed for autonomous AI agent orchestration. It implements the innovative "Ralph Wiggum technique," a methodology focused on continuous iteration to ensure AI agents complete complex tasks effectively. This powerful tool supports multiple AI backends and offers features like a "hat system" for specialized personas and human-in-the-loop interaction via Telegram.
AgentFS: The Filesystem Designed for AI Agents and Their State Management
AgentFS is an innovative filesystem specifically engineered for AI agents, providing robust storage abstractions. It leverages SQLite to offer auditability, reproducibility, and portability for agent states, tool calls, and file operations. This solution simplifies debugging, analysis, and deployment of AI agents by encapsulating their entire runtime into a single, queryable database file.
EnvHarness: Dynamically Adapting Environments for Agent Learning
EnvHarness empowers large language models (LLMs) acting as autonomous agents to learn more effectively from interactive environments. It achieves this by wrapping static environments with plug-in components, making them dynamically controllable without altering their internal code. This innovative approach allows environments to target specific agent weaknesses and continuously teach as agents improve, leading to more effective and efficient learning outcomes.
github-tools: Seamless GitHub API Integration for Vercel AI SDK Agents
github-tools offers a powerful collection of GitHub tools and agents specifically designed for the Vercel AI SDK. This project enables developers to effortlessly wrap GitHub's API as AI SDK tools, making them ready to plug into any AI agent. It significantly simplifies the creation of intelligent applications that interact with GitHub.
Mityu: Privacy-First Local AI Meeting Assistant for macOS & Windows
Mityu is a privacy-first, local-first AI meeting assistant built with Rust and Tauri. It offers live transcription using Parakeet/Whisper, speaker diarization, and Ollama summarization, all processed 100% locally without cloud requirements. This desktop application is available for macOS and Windows, ensuring sensitive conversations remain on your device.
gh-aw: Automating GitHub Workflows with AI Agents
GitHub Agentic Workflows (gh-aw) is a powerful GitHub CLI extension that enables AI-powered repository automation. It allows developers to define intelligent, agentic workflows using Markdown with YAML frontmatter, which are then compiled into standard GitHub Actions workflows. This tool complements traditional CI/CD by handling tasks requiring reasoning or interpretation, such as issue triage and pull request reviews, leveraging AI engines like GitHub Copilot and Claude Code.
free-claude-code: Connect Coding Agents to Multiple AI Models
Free Claude Code is a local proxy and admin interface for routing coding agents to cloud and local language models. It suits developers who want one place to configure providers, switch models, and connect multiple coding clients.
claude-video: Empowering Claude to Watch and Analyze Any Video Content
The claude-video repository provides a powerful tool, `/watch`, enabling Claude to process and understand video content. It automates the download, frame extraction, and transcription of any video, feeding this rich data to Claude. This allows Claude to answer questions and provide insights grounded in what it has actually seen and heard.
ds4: A Fast Local Inference Engine for DeepSeek V4 Flash and PRO on Metal, CUDA, ROCm
ds4 is a highly optimized, native inference engine designed for DeepSeek V4 Flash and PRO models. It provides efficient local inference across various hardware platforms, including Apple Silicon (Metal), NVIDIA GPUs (CUDA), and AMD ROCm. This project focuses on delivering high performance for large language models on consumer-grade machines.
AntiVibe: Learn Code with AI-Powered Deep Dives and Architectural Audits
AntiVibe is an innovative code learning and audit framework designed to help developers truly understand code, whether it's AI-generated, new, or legacy. It transforms any codebase into educational deep dives or senior-level architectural audits, moving beyond mere code summaries to explain the 'what,' 'why,' and 'when' of code patterns. This tool addresses the common problem of developers copying AI-generated code without grasping its underlying logic or implications.