FlashInfer: Kernel Library for LLM Serving
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 1040 个。
想找可以部署在 Cloudflare 免费套餐上的项目？看 Cloudflare 开源
全部 1040🧠 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 36🎨 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 76🧪 评测·观测·安全 81🚪 API 网关与代理 12🔎 搜索与深度研究 14⚙️ 深度学习基础库 57🏷️ 数据与标注 30🔬 行业与科研 AI 34⚡ 效率工具 14
Julep — durable, composable AI agents. Flows that crash and resume, retry safely, and explain every step.
Open-source framework for building agentic apps in JavaScript, Go, Dart, and Python, built and used in production by Google
非线智能 NoneLinear - ReLE评测：中文AI大模型能力评测（持续更新）：目前已囊括374个大模型，覆盖chatgpt、gpt-5.4、谷歌gemini-3.1-pro、Claude-4.6、文心ERNIE-X1.1、ERNIE-5.0、qwen3.6-max、qwen3.6-plus、百川、讯飞星火、商汤senseChat等商用模型， 以及step3.5-flash、kimi-k2.6、ernie4.5、MiniMax-M
Open source AI clip generator: turns long videos into viral 9:16 shorts with AI moment detection, face tracking, subtitles and dubbing. Self-host free with Docker (MIT), or use the cloud with GPU speed from $12/mo. MCP s
AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.
基于深度学习的文档文字识别库。
A flexible, high-performance serving system for machine learning models
🐬DeepChat - A smart assistant that connects powerful AI to your personal world
《深入理解 AI Infra：量化分析与系统设计》（李博杰 著）开源书稿：从硬件约束和模型架构出发，量化推导 LLM 推理与训练系统设计。含全书正文、PDF、配套计算工具与实验
Aim 💫 — An easy-to-use & supercharged open-source experiment tracker.
A control plane with a durable state kernel for long-horizon agents and teams. Keep work moving and improving across sessions, with less human attention.
开源 LLM 可观测平台，一行代码接入监控与缓存。
an ambient intelligence library
HelixDB is an OLTP graph database with native vector and full-text search built in Rust on Object Storage.
A scikit-learn compatible neural network library that wraps PyTorch
按语义智能路由请求到合适模型的 Mixture-of-Models 路由器。
Standardized Distributed Generative and Predictive AI Inference Platform for Scalable, Multi-Framework Deployment on Kubernetes
Local-first session search, analytics, insights, and token use statistics for coding agents, supporting Claude Code, Codex, and more than 20 other agents.
The CLI and skills that turn any coding assistant into an expert at creating, evaluating, and deploying AI agents on Google Cloud.
Framework for evaluating and improving agents
A simple SWE style browser+desktop agent framework that achieves SOTA results on long horizon web tasks.
A system for quickly generating training data with weak supervision
SWE-bench: Can Language Models Resolve Real-world Github Issues?