Hugging Face 的小而强的语言模型系列及完整训练配方。
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
Easiest and laziest way for building multi-agent LLMs applications.
Generative models for conditional audio generation
LeanCTX — Context Gateway for AI Systems. Control what your AI can see. Open-source Engine for context selection, supported controls, and evidence.
State-of-the-art LLM compression, built for production inference with vLLM
Open-source security automation platform for teams and AI agents
A flexible, high-performance 3D simulator for Embodied AI research.
Paper2Agent is a multi-agent AI system that automatically transforms research papers into interactive AI agents.
Genmo 的开源视频生成模型，动作流畅。
AI Infra / AI Orchestration / AI Control Plane
Fully customizable AI chatbot component for your website
Power CLI and Workflow manager for LLMs (core package)
Open-source multimodal retrieval engine (Morphik Core)
Eagle: Frontier Vision-Language Models with Data-Centric Strategies
基于 AI Agent + MCP 工具链 + 渗透 Skill 编排， 配合大语言模型， 自然语言输入 → 自动完成「信息收集 → 漏洞发现 → 漏洞利用 → 报告生成」全流程。
Personal AI Notebooks. Organize files & webpages and generate notes from them. Open source, local & open data, open model choice (incl. local).
评估与追踪 LLM 应用实验。
Stateful agents that are like people, with memory, identity, and the ability to learn and adapt
⚡FlashRAG: A Python Toolkit for Efficient RAG Research (WWW2025 Resource)
A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on Hopper, Ada and Blackwell GPUs, to provide better performance with lower memory util
Synthetic data generation for tabular data
DeepResearchAgent is a hierarchical multi-agent system designed not only for deep research tasks but also for general-purpose task solving. The framework leverages a top-level planning agent to coordinate multiple specia
开源的 AI 搜索引擎，可本地或云端模型驱动。
A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.