Best AI GitHub Repos
Browse 433 repos. Filter by type or sort.
legalzoom/legalzoom
Attorney guidance and legal tools for business and personal needs. AI-powered document review identifies critical risks and important clauses, advises when to engage an attorney, and routes to LegalZoom's network when professional expertise is needed.
danny-avila/LibreChat
Enhanced ChatGPT Clone: Features Agents, MCP, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure, Groq, o1, GPT-5, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message search, Code Interpreter, langchain, DALL-E-3, OpenAPI Actions, Functions, Secure Multi-User Auth, Presets, open-source for self-hosting. Active.
anthropics/life-sciencesOfficial
Repo for the Claude Code Marketplace to use with the Claude for Life Sciences Launch. This will continue to host the marketplace.json long-term, but not the actual MCP servers.
HKUDS/LightRAG
[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"
anthropics/linearOfficial
Linear issue tracking integration. Create issues, manage projects, update statuses, search across workspaces, and streamline your software development workflow with Linear's modern issue tracker.
Shopify/liquid-lsp
LSP integration for Shopify Liquid templates via the Shopify CLI theme language server.
Shopify/liquid-skills
Liquid language support plugin for Claude Code
BerriAI/LiteLLM
Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, VLLM, NVIDIA NIM]
hiyouga/LLaMA-Factory
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
ggml-org/llama.cpp
LLM inference in C/C++
run-llama/LlamaIndex
LlamaIndex is the leading document agent and OCR platform
rasbt/LLMs-from-scratch
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
lobehub/lobehub
🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.
/LobeHub Skills
Skill ecosystem for the LobeChat open-source AI assistant. Extend your LobeChat instance with plugins, tools, and custom capabilities.
mudler/LocalAI
LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
pydantic/logfire
AI observability platform for production LLM and agent systems.
anthropics/lua-lspOfficial
# lua-lsp Lua language server for Claude Code, providing code intelligence and diagnostics. ## Supported Extensions `.lua` ## Installation ### Via Homebrew (macOS) ```bash brew install lua-language-server ``` ### Via package manager (Linux) ```bash # Ubuntu/Debian (via snap) sudo snap install lua-language-server --classic # Arch Linux sudo pacman -S lua-language-server # Fedora sudo dnf install lua-language-server ``` ### Manual Installation Download pre-built binaries from the [releases
ory/lumen
Reduce Claude Code, Codex, OpenCode wall clock and token use by 50% with open source, local semantic search. Works for small and large codebases and monorepos! Enterprise-ready and fully compliant via Ollama and SQLite-vec.
lusha-oss/lusha
Prospect, enrich, and build call-ready lead lists using Lusha's B2B intelligence platform — verified phone numbers, company signals, and lookalike targeting.
mapbox/mapbox
Mapbox skills and MCP servers for building location-aware applications with AI. Includes geospatial tools, style management, and patterns for web, iOS, Android, and AI agent frameworks.
anthropics/math-olympiadOfficial
# math-olympiad Competition math solver with adversarial verification. ## The problem Self-verification gets fooled. A verifier that sees the reasoning is biased toward agreement. ArXiv:2503.21934 ("Proof or Bluff") showed 85.7% self-verified IMO success drops to <5% under human grading. ## The approach - **Context-isolated verification**: verifier sees only the clean proof, never the reasoning trace - **Pattern-armed adversarial checks**: not "is this correct?" but "does this accidenta
modelcontextprotocol/MCP ServersOfficial
Model Context Protocol Servers
modelcontextprotocol/mcp-apps
Skills for creating MCP Apps with the MCP Apps SDK
doobidoo/mcp-memory-service
Open-source persistent memory for AI agent pipelines (LangGraph, CrewAI, AutoGen) and Claude. REST API + knowledge graph + autonomous consolidation.
Everything AI. One email. Every Monday.
New tools. Model launches. Plugins. Repos. Tactics. The moves the sharpest builders are making right now, before everyone else. 5-minute read.