Open-source workflow automation platform with native AI nodes and hundreds of service integrations.
AI Open Source
Hand-picked AI open-source projects on GitHub worth following: LLMs, agents, RAG, local deployment, image and speech… 1043 projects so far.
Looking for projects you can deploy for free on Cloudflare, Vercel, Netlify and more? See Free Deploy Picks
All 1043🧠 Large Language Models 25🤖 AI Agents 161🧩 App Development Platforms 22📚 RAG & Knowledge Bases 48💬 Chat UIs & Clients 40🖥️ Local Inference & Deployment 87👨💻 AI Coding 97🛠️ Frameworks & SDKs 47🔌 MCP & Tool Ecosystem 35🎨 Image Generation 26🎬 Video Generation 17🎙️ Speech & Audio 46👁️ Computer Vision 26📄 Document Parsing & Scraping 25🗄️ Vector Databases 24🏋️ Training, Fine-Tuning & MLOps 71🧪 Evaluation, Observability & Safety 79🚪 API Gateways & Proxies 12🔎 Search & Deep Research 15⚙️ Deep Learning Libraries 58🏷️ Data & Annotation 32🔬 Industry & Science AI 34⚡ Productivity Tools 16
Google's end-to-end machine learning platform with a complete ecosystem.
A scraping API that turns entire websites into LLM-ready Markdown or structured data.
The project that sparked the autonomous-agent wave, now a complete platform for building and running AI agents.
Run Llama, Qwen, DeepSeek and other large models locally with one command, with a built-in model library and OpenAI-compatible API.
A unified interface to tens of thousands of pre-trained models covering text, images, audio and multimodal tasks.
The classic Stable Diffusion web UI, with a huge plugin ecosystem.
An open-source LLM app development platform: visual workflow orchestration, RAG and agents, with one-click API publishing.
The most popular self-hosted AI interface, supporting Ollama and OpenAI-compatible backends, usable offline.
The most popular framework for building LLM apps, offering chains, tools, memory and a large number of integrations.
The most powerful node-based diffusion-model interface and backend, with visual, reusable workflows.
A pure C/C++ LLM inference engine supporting CPU, GPU and Apple Silicon with GGUF quantization, plus a built-in OpenAI-compatible server.
OpenAI's terminal coding agent that reads your code locally and carries out tasks.
Let AI agents operate the browser directly to browse the web, fill in forms and more.
OpenAI's open-source general-purpose speech recognition model, supporting multilingual transcription and translation.
Google's open-source terminal AI agent: use Gemini right from the command line.
A deep-learning framework with dynamic computation graphs, the mainstream choice in both research and industry.
DeepSeek's open-source MoE large model, rivaling top closed-source models in performance at very low training cost.
A high-throughput, low-memory LLM inference and serving engine, with PagedAttention as its core technique.
An open-source RAG engine built on deep document understanding, with traceable citations, ready to use out of the box.
DeepSeek's reasoning model, which elicits long chain-of-thought ability through reinforcement learning and open-sources distilled small models.
A collection of the official reference implementations of Model Context Protocol servers, covering files, Git, databases and more.
Baidu PaddlePaddle's OCR toolkit, combining over a hundred languages, PP-OCR and document parsing.
An open-source AI software engineer platform (formerly OpenDevin) that can autonomously write code, run commands and browse the web.