Open Source
Explore the latest AI open-source projects from GitHub and HuggingFace.
Explore the latest AI open-source projects from GitHub and HuggingFace.
Explore the latest AI open-source projects from GitHub and HuggingFace. Discover projects across categories like LLM, Vision, Audio, and more.
625 projects
inclusionAI (Ant Group / Tsinghua IIIS)
Fully asynchronous reinforcement learning system for LLM reasoning and agents, achieving 2.77x speedup over synchronous training with state-of-the-art results on math and coding benchmarks
Microsoft
Microsoft's comprehensive 11-module open-source curriculum teaching Model Context Protocol with hands-on labs in 6 languages, 14.9K stars and 50+ translations
Jam with AI
Seven-week hands-on course building production-grade RAG systems with Docker, OpenSearch, FastAPI, Ollama, and LangGraph agentic workflows, with 3.6K GitHub stars
Jeffallan
66 specialized skills for full-stack developers that transform Claude Code into an expert pair programmer, covering 12 categories from languages and frameworks to security and ML with progressive disclosure architecture
Anthropic
Official Anthropic GitHub Action that uses Claude for AI-powered security review of pull request code changes, detecting vulnerabilities with semantic understanding across all programming languages
Blaizzy (Prince Canuma)
Python package for inference and fine-tuning Vision Language Models on Mac using Apple's MLX framework, supporting multimodal inputs including images, audio, and text with local GPU acceleration
Aider-AI
Terminal-based AI pair programming tool with 41.5K stars that edits code in real Git repos through natural language, supporting Claude, GPT, DeepSeek, and 100+ languages
ZHZisZZ
Unified open-source framework for training, inference, and evaluation of diffusion language models with Fast-dLLM acceleration and support for LLaDA, Dream, and BERT-Chat
TheCraigHewitt
Open-source Claude Code workspace with 10 specialized agents and 15+ commands for automated SEO content research, writing, optimization, and performance tracking
LMCache
Open-source KV cache optimization layer for LLM serving that delivers 3-10x faster inference by reusing cached computations across requests and instances
agentscope-ai
Open-source agent memory management framework with file-based and vector-based systems for persistent, searchable memory across sessions
shareAI-lab
Educational open-source repository that teaches building a production AI coding agent from scratch through 12 progressive sessions, each introducing one architectural mechanism