Open-source self-hosted AI agent runtime and multi-agent framework for autonomous agent swarms. Agent memory, MCP tools, schedules, delegation, and 23+ LLM providers (Claude, GPT, Gemini, OpenRouter, Ollama). A practical
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 1038 个。
想找可以部署在 Cloudflare 免费套餐上的项目？看 Cloudflare 开源
全部 1038🧠 大语言模型 26🤖 AI 智能体 162🧩 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 87👨💻 AI 编程 96🛠️ 开发框架与 SDK 47🔌 MCP 与工具生态 36🎨 图像生成 24🎬 视频生成 18🎙️ 语音与音频 43👁️ 计算机视觉 27📄 文档解析与抓取 24🗄️ 向量数据库 23🏋️ 训练微调与 MLOps 73🧪 评测·观测·安全 78🚪 API 网关与代理 12🔎 搜索与深度研究 15⚙️ 深度学习基础库 58🏷️ 数据与标注 27🔬 行业与科研 AI 37⚡ 效率工具 13
Open weights language model from Google DeepMind, based on Griffin.
Create 🐍 Python AI Actions and 🤖 Automations, and deploy & operate them anywhere
Jarvis AI Assistant - Voice-powered AI assistant for Mac
Think before doing, prove before saving. Vestige is a local, deterministic safety kernel for AI agents. Every memory write and agent action is recorded in Strata, a signed, append-only log, so you can see exactly what yo
Self-hosted AI Agents Platform supporting Claude Code, Codex, Gemini agents. Apache 2.0.
Your thinking deserves a map: an infinite canvas where LLM conversations grow into an editable thought graph. Wires are the context.
Context Engine for your long-running AI agents
The fastest developer workflow for every AI coding agent. Live status, quick prompts, worktrees, and diff review from one tmux TUI.
AI 网关与多渠道代理，自带计费和监控。
Open framework for confidential AI
Open Model Engine (OME) — Kubernetes operator for LLM serving, GPU scheduling, and model lifecycle management. Works with SGLang, vLLM, TensorRT-LLM, and Triton
The action firewall for AI agents. Enforce policy and human approval before risky tool calls, shell commands, workflows, and production changes, with auditable evidence.
电子发票整理与报销准备工具：从邮箱批量收集 PDF/OFD/XML 发票，OCR 识别、分类归档并生成 Excel 汇总；提供 Windows/macOS 桌面版与 DSH 插件。
Multi-harness control plane for Claude Code, Codex, Cursor, and OpenCode: quota-aware rotation across multiple Claude/Codex subscriptions, shared thread context, and cross-model review.
Local gateway for Claude Code, Codex and other AI clients on macOS, Windows and Linux: switch upstreams without touching clients, keep API keys from relays, cut off malicious tool calls, trace every request.
Caura (formerly MemClaw) — governed shared memory for AI agent fleets. Multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies, audit trails, knowledge graph, self-improving retrieval. Apache 2.0.
Open-source database & workspace for AI agents — structured data, durable knowledge, reusable skills, runnable apps, and human review on the writes that matter. Local-first and self-hostable.
Accelerate your Neural Architecture Search (NAS) through fast, reproducible and modular research.
Cut AI context cost without trusting the compressor. Every reduction is reversible, byte-exact recoverable, and carries an auditable receipt. Local-first, works through proxy, MCP, SDK, or agent wrapper.
Your First LLM-Wiki Conversation Knowledge Base
MindSQL: A Python Text-to-SQL RAG Library simplifying database interactions. Seamlessly integrates with PostgreSQL, MySQL, SQLite, Snowflake, and BigQuery. Powered by GPT-4 and Llama 2, it enables natural language querie
Python package for LLM compression
The collaboration layer for AI teams: domain experts annotate and review agent behavior, engineers improve the agent from what they find.