449 个
可直接用于生产环境的 Agent 工作流开发平台。Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
友好的 AI 交互界面（支持 Ollama、OpenAI API 等）。User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
100+ 可真正运行的 AI Agent 与 RAG 应用——克隆、定制、上线。100+ AI Agents, Agent Skills and RAG Apps - Free and Open Source.
将任何代码库及其文档、SQL schema、配置文件和 PDF 转化为可查询的知识图谱。适用于 Claude Code、Cursor、Codex 和 Gemini CLI 的 /graphify skill：本地确定性 AST 解析，每条边都有解释，无需向量存储。Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
为每个 Agent 提供跨会话持久上下文——捕获会话中 Agent 的所有行为，经 AI 压缩后注入到未来会话中。支持 Claude Code、OpenClaw、Codex、Gemini、Hermes、Copilot、OpenCode 等。Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
RAGFlow 是一款领先的开源 RAG 引擎，融合前沿 RAG 与 Agent 能力，为 LLM 构建更优的上下文层。RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
将任意 PDF 或图片文档转换为结构化数据供 AI 使用。强大而轻量的 OCR 工具集，弥合图像/PDF 与 LLM 之间的鸿沟，支持 100+ 种语言。Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
一个开源的长时程 SuperAgent harness，可研究、编码与创作。借助 sandbox、记忆、工具、Skill、subagent 与 message gateway，处理耗时从分钟到小时不等的多层级任务。An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.
面向 prompt engineering、context engineering、RAG 和 AI Agent 的指南、论文、课程、notebook 与资源。🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.
AI 编程助手 Skill（兼容 Claude Code、Codex、OpenCode、Cursor、Gemini CLI 等），可将任意代码、SQL schema、R 脚本、shell 脚本、文档、论文、图片或视频文件夹转换为可查询的知识图谱，应用代码、数据库 schema 与基础设施统一于一张图谱中。AI coding assistant skill (Claude Code, Codex, OpenCode, Cursor, Gemini CLI, and more). Turn any folder of code, SQL schemas, R scripts, shell scripts, docs, papers, images, or videos into a queryable knowledge graph. App code + database schema + infrastructure in one graph.
将 PDF、Office 文档等复杂文档转换为 LLM 就绪的 markdown/JSON，适配 Agentic workflow。Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
12 节课入门 AI Agent 构建。18 Lessons to Get Started Building AI Agents
🌊 领先的 Agent 元编排框架。部署智能多角色蜂群、调度自主工作流、构建对话式 AI 系统。自带自适应记忆、自学习智能、RAG 集成，原生支持 Claude Code / Codex / Hermes 等众多工具🌊 The original agent meta-harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, RAG integration, and native Claude Code / Codex / Hermes and many more Integrated
在 tool 输出、日志、文件与 RAG chunks 进入 LLM 之前进行压缩，token 减少 60-95%，答案保持不变。可作为库、proxy 或 MCP server 使用。Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
停止租用你的智能。用 AnythingLLM 拥有它。本地优先的 Agent 体验所需的一切Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience
开箱即用的云模板，支持 RAG、AI 流水线与企业级搜索，接入实时数据。🐳Docker 友好。⚡始终与 Sharepoint、Google Drive、S3、Kafka、PostgreSQL 以及各类实时数据 API 保持同步。Ready-to-run cloud templates for RAG, AI pipelines, and enterprise search with live data. 🐳Docker-friendly.⚡Always in sync with Sharepoint, Google Drive, S3, Kafka, PostgreSQL, real-time data APIs, and more.
面向本地模型上私有 AI 应用的完整 API 层：涵盖 RAG、skill、tool、MCP、text-to-sql 等。兼容任意 OpenAI 兼容的推理服务。Complete API layer for private AI applications on local models: RAG, skills, tools, MCP, text-to-sql, and more. Works with any OpenAI-compatible inference server.
LlamaIndex 是领先的文档 Agent 与 OCR 平台。LlamaIndex is the leading document agent and OCR platform
【低代码迈入v2.0时代，一句话即可生成整个系统】企业级AI低代码平台，一键生成前后端代码甚至整个系统。 AI Skills 一句话画流程、设计表单、生成报表、大屏。内置 AI应用平台涵盖：AI聊天、知识库、流程编排、MCP插件等，兼容主流大模型。引领AI低代码「Skills 生成 → 在线配置 → 代码生成 → 手工合并->AI修改」开发模式，解决 Java 项目 90% 重复工作，提高效率又不失灵活。
Milvus 是一款高性能、云原生的向量数据库，专为可扩展的向量 ANN 搜索而构建。Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search
《深入理解 AI Agent：设计原理与工程实践》（李博杰 著）开源主仓库：全书正文、编译版 PDF 与按章配套代码
[EMNLP2025] "LightRAG:简单且快速的检索增强生成"[EMNLP2025] LightRAG: Simple and Fast Retrieval-Augmented Generation
高性能代码智能 MCP server。将代码库索引为持久化知识图谱，平均仓库仅需毫秒级。支持 158 种语言，亚毫秒级查询，token 用量减少 99%。单一静态二进制，零依赖。High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.
深入讲解 LLM、RAG 以及真实场景 AI Agent 应用的教程。In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
你的 AI 第二大脑，支持自托管。可从网页或本地文档获取答案，构建自定义 Agent，编排自动化任务，执行深度研究。将任意在线或本地 LLM（gpt、claude、gemini、llama、qwen、mistral）转变为你的个人自主 AI。立即免费开始。Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free.
DeepTutor:Agent 原生的个性化辅导系统。https://deeptutor.info/DeepTutor: Lifelong Personalized Tutoring. https://deeptutor.info/.
模块化的、基于图结构的 Retrieval-Augmented Generation (RAG) 系统。A modular graph-based Retrieval-Augmented Generation (RAG) system
📑 PageIndex：面向无向量、基于推理的 RAG 的文档索引📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG