为扩散模型加入边缘、姿态等条件控制的经典方案。
AI Open Source
Hand-picked AI open-source projects on GitHub worth following: LLMs, agents, RAG, local deployment, image and speech… 1040 projects so far.
Looking for projects you can deploy for free on Cloudflare, Vercel, Netlify and more? See Free Deploy Picks
All 1040🧠 Large Language Models 24🤖 AI Agents 159🧩 App Development Platforms 23📚 RAG & Knowledge Bases 47💬 Chat UIs & Clients 41🖥️ Local Inference & Deployment 87👨💻 AI Coding 97🛠️ Frameworks & SDKs 46🔌 MCP & Tool Ecosystem 36🎨 Image Generation 26🎬 Video Generation 17🎙️ Speech & Audio 45👁️ Computer Vision 26📄 Document Parsing & Scraping 25🗄️ Vector Databases 25🏋️ Training, Fine-Tuning & MLOps 71🧪 Evaluation, Observability & Safety 79🚪 API Gateways & Proxies 12🔎 Search & Deep Research 16⚙️ Deep Learning Libraries 57🏷️ Data & Annotation 32🔬 Industry & Science AI 33⚡ Productivity Tools 16
💫 Industrial-strength Natural Language Processing (NLP) in Python
自托管的 AI 代码补全服务，可作为 GitHub Copilot 的本地替代。
极简的深度学习框架，介于 PyTorch 与 micrograd 之间。
GitHub 官方 MCP 服务器，让 AI 直接管理仓库、Issue 与 PR。
逐步引导 AI 开发完整应用的开发者助手。
Visualizer for neural network, deep learning and machine learning models
Build and run agents you can see, understand and trust.
开源的 AI 聊天界面模板，易于自托管与二次开发。
开源的多语言文本转语音，支持零样本克隆。
OpenMMLab 的目标检测工具箱。
对接公司各类知识源的开源 AI 搜索与聊天平台（原 Danswer）。
Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory with small models for free
Conductor is an event driven agentic workflow engine providing durable and highly resilient execution engine for applications and AI Agents
Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.
OfficeCLI is the first and best Office suite purpose-built for AI agents to read, edit, and automate Word, Excel, and PowerPoint files. Free, open-source, single binary, no Office installation required.
Build Real-Time Knowledge Graphs for AI Agents
用大模型和图逻辑驱动的 Python 网页抓取库。
Privacy first, AI meeting assistant with 4x faster Parakeet/Whisper live transcription, speaker diarization, and Ollama summarization built on Rust. 100% local processing. no cloud required. Meetily (Meetly Ai - https://
斯坦福的 LLM 知识策展系统，从零研究并撰写带引用文章。
Community plugin to control Blender 3D with any LLM of your choice. Not affiliated with the official Blender Foundation.
组织 PyTorch 代码的轻量封装，专注研究而非样板。
简洁的 ChatGPT 网页应用，使用 Express 与 Vue3 构建。
Memory and context engine + app that is extremely fast, scalable, and can be run fully locally. The Memory API for the AI era.