在 Intel CPU / GPU / NPU 上加速运行与微调大模型。
AI 开源项目
精选 GitHub 上值得关注的 AI 开源项目：大模型、智能体、RAG、本地部署、图像与语音……共收录 1037 个。
想找可以部署在 Cloudflare 免费套餐上的项目？看 Cloudflare 开源
全部 1037🧠 大语言模型 25🤖 AI 智能体 160🧩 应用开发平台 23📚 RAG 与知识库 47💬 聊天界面与客户端 42🖥️ 本地推理与部署 85👨💻 AI 编程 95🛠️ 开发框架与 SDK 46🔌 MCP 与工具生态 35🎨 图像生成 25🎬 视频生成 18🎙️ 语音与音频 43👁️ 计算机视觉 27📄 文档解析与抓取 25🗄️ 向量数据库 25🏋️ 训练微调与 MLOps 74🧪 评测·观测·安全 81🚪 API 网关与代理 12🔎 搜索与深度研究 15⚙️ 深度学习基础库 57🏷️ 数据与标注 29🔬 行业与科研 AI 34⚡ 效率工具 14
🧙 Build, run, and manage data pipelines for integrating and transforming data.
Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.
AWS 开源的模型驱动智能体 SDK，几行代码即可构建 Agent。
Build an agent harness and control it end-to-end. Open-source SDK for production AI agents in Python & TypeScript - any model, any cloud.
AI Toolkit for Healthcare Imaging
Open-source, high-performance AI gateway that works as your LLM gateway, MCP gateway and agent gateway. One OpenAI-compatible API for 10,000+ models, with failover, load balancing, semantic caching, virtual keys, budgets
Let AI agents use your real, logged-in browser without interrupting your work. CLI + extension for browser automation across any shell-capable AI agent.
an open-source alternative to the dots, bots and muses of the world, run an office of claude code/codex like agents on your laptop, sandboxes or anywhere, uses your existing subscriptions
Apache Beam is a unified programming model for Batch and Streaming data processing.
🧱 easy, fast, programmable and local-first microVM runtime and library
slime is an LLM post-training framework for RL Scaling.
An app that brings language models directly to your phone.
Manage multiple AI terminal agents like Claude Code, Codex, OpenCode, and Amp.
Accessible large language models via k-bit quantization for PyTorch.
A library of Agent Skills designed to work with the Stitch MCP server. Each skill follows the Agent Skills open standard, for compatibility with coding agents such as Antigravity, Gemini CLI, Claude Code, Cursor.
An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.
The sandbox agent framework.
Meta 的生成式 AI 应用标准化接口与参考实现。
The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >74% on SWE-bench verified!
通义千问的图像生成基础模型，擅长复杂文字渲染。
World's first open-source enterprise world model.
A Datacenter Scale Distributed Inference Serving Framework
用本地 AI 模型辅助浏览的 Chrome / Firefox 侧边栏扩展。