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
datawhalechina
Datawhale's 44.8k-star open tutorial teaching LLM agent development from scratch, covering ReAct, LangGraph, AutoGen, memory systems, and full capstone projects.
HKUDS
Agent-native trading platform where AI agents publish signals, copy trades, and collaborate with humans across all major markets via a collective intelligence layer.
z-lab
Lightweight block diffusion model that accelerates LLM inference via speculative decoding, supporting vLLM, SGLang, Transformers, and MLX with sub-2x walltime overhead.
rtk-ai
Single Rust binary CLI proxy that cuts LLM token usage 60-90% by filtering and compressing command outputs before they reach the AI agent's context window.
huggingface
Hugging Face's open-source agent that independently researches, writes, and deploys ML code using the entire HF ecosystem.
zilliztech
Semantic code search MCP plugin for AI coding agents — hybrid BM25 + vector search, AST chunking, 40% token reduction.
Q00
An Agent OS that transforms vague ideas into verified codebases through a specification-first workflow — stop prompting, start specifying.
Google's open-source Python framework for building, evaluating, and deploying AI agents — code-first, Gemini-optimized, deployable to Cloud Run and Vertex AI.
openai
OpenAI's official lightweight Python SDK for building multi-agent workflows — provider-agnostic, with built-in tracing, guardrails, and voice agent support.
safishamsi
Open-source tool that transforms code repositories, documentation, PDFs, images, and videos into interactive queryable knowledge graphs — runnable with a single /graphify . command from any AI coding assistant.
bytedance
ByteDance's open-source super agent framework that orchestrates sub-agents, memory systems, and Docker sandboxes for complex multi-step tasks spanning research, coding, and content creation.
NousResearch
Nous Research's self-improving AI agent that autonomously creates skills, maintains persistent memory across sessions, and runs across cloud VPS, serverless platforms, and mobile (Android Termux).