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.
760 projects
langgenius
Production-ready open-source LLM application platform with visual workflow builder, RAG pipeline, and agent capabilities, boasting 130K+ GitHub stars.
mastra-ai
TypeScript AI agent framework from the Gatsby team, offering workflows, agents, RAG, and MCP server support with 40+ AI provider integrations.
infiniflow
Leading open-source RAG engine with deep document understanding, grounded citations, and agent capabilities, with 73K+ GitHub stars.
p-e-w
Fully automatic censorship removal tool for transformer-based language models using directional ablation with Optuna optimization.
obra
Agentic skills framework enforcing test-driven development, systematic debugging, and multi-agent orchestration for AI coding assistants.
Alibaba
Alibaba's lightweight in-process vector database built on Proxima, enabling millisecond similarity search across billions of vectors without servers.
Letta AI
Memory-first coding agent that persists learning across sessions and supports multiple LLM providers including Claude, GPT, and Gemini.
OpenClaw
Open-source personal AI assistant connecting to 13+ messaging platforms with local gateway architecture, voice support, and multi-agent routing.
ruvnet
Production-grade WiFi-based human pose estimation system enabling real-time full-body tracking through walls with sub-50ms latency and no cameras required.
QwenLM
Alibaba's 397B MoE LLM with hybrid attention, 201-language support, and 8x inference efficiency
Google's open-source Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.
Moonshine AI
Open-source ASR toolkit for edge devices that outperforms Whisper Large v3 with 6x fewer parameters and 44x faster inference, running on-device across all major platforms.