didilili
★ 4,647ai-agents-from-zero
🚀 2026 最系统的 AI Agent 速成指南｜智能体实战教程 · 完整学习路径 + 实战项目 + 面试题库 · 对标大模型应用开发工程师岗位 · 覆盖LangChain / LangGraph / Coze / Dify / MCP / skills / LLM / RAG / 提示词 · 企业级部署与微调 · 从0到企业级落地 + 从学习到上线项目 + 面试准备一体化
AI 频道AI 智能体 
开源 AI 智能体
AI 智能体是一种用大模型决定下一步做什么的程序：它会调用浏览器、代码解释器或 API 等工具，反复执行，直到任务完成。这里的项目既有用来搭建自己智能体的框架，也有能写代码、浏览网页或运行业务流程的现成智能体。
怎么选
比较时看三点：能用哪些模型——只支持一家服务商，还是任何兼容 OpenAI 接口的端点（包括本地模型）；怎么限制智能体能做的事——沙箱、审批步骤、权限清单；以及它能否在步骤之间、会话之间保留记忆。会执行代码或命令行的智能体应该在沙箱里运行，给它访问你电脑的权限之前先确认这一点。
Star 最多的项目
第 145–168 个，共 426 个rivet-dev
★ 4,631agentos
Give agents an operating system as a library. Runs in your existing backend – no sandboxes, VMs, or SaaS. Powered by WebAssembly & V8 isolates.
ruc-datalab
★ 4,623DeepAnalyze
DeepAnalyze is the first agentic LLM for autonomous data science. 🎈你的AI数据分析师，自动分析大量数据，一键生成专业分析报告！
JetBrains
★ 4,572koog
Koog is a JVM (Java and Kotlin) framework for building predictable, fault-tolerant and enterprise-ready AI agents across all platforms – from backend services to Android and iOS, JVM, and even in-browser environments. Koog is based on our AI products expertise and provides proven solutions for complex LLM and AI problems
skyzh
★ 4,567tiny-llm
learn LLM inference system on Apple Silicon for systems engineers: build a tiny vLLM + Qwen
VectifyAI
★ 4,520OpenKB
OpenKB: Open LLM Knowledge Base
FareedKhan-dev
★ 4,507all-agentic-architectures
35 production-grade agentic AI architectures (Reflexion, LATS, GraphRAG, MemGPT, Voyager, BrowserAgent, ...) — a Python library and runnable textbook with multi-provider LLM support and a 17-task benchmark leaderboard.
FlowElement-xinliuyuansu
★ 4,501m_flow
A bio-inspired cognitive memory engine — a new paradigm for Graph RAG.
CaviraOSS
★ 4,499LongMemory
Local persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc.
daveebbelaar
★ 4,461ai-cookbook
Examples and tutorials to help developers build AI systems
gptme
★ 4,415gptme
Your agent in your terminal, equipped with local tools: writes code, uses the terminal, browses the web. Make your own persistent autonomous agent on top!
cs-lazy-tools
★ 4,387ChatGPT-On-CS
拼多多、千牛、抖店 AI 客服机器人：自动回复客户咨询、商品答疑、售后申诉处理，支持微信、小红书、京东、抖音、B站、微博等多平台统一接待；可接入 DeepSeek / 通义千问 等大模型，支持自有知识库定制。
walkinglabs
★ 4,385hands-on-modern-rl
🚀 An open-source, hands-on curriculum bridging the gap from basic RL concepts to LLM alignment, RLVR, and advanced Agentic systems.
crmne
★ 4,369ruby_llm
One delightful Ruby framework for every major AI provider. Build AI agents, chatbots, RAG apps, and multimodal workflows in beautiful, expressive code.
SenteLabsAI
★ 4,320OpenExecutive
AI-powered virtual executive team — a single coherent executive persona backed by 8 specialist agents (FastAPI + Next.js).
deepflowio
★ 4,264deepflow
eBPF Observability - Distributed Tracing and Profiling
algorithmicsuperintelligence
★ 4,263optillm
Optimizing inference proxy for LLMs
lintsinghua
★ 4,243claude-code-book
《御舆：解码 Agent Harness》42万字拆解 AI Agent 的Harness骨架与神经 —— Claude Code 架构深度剖析，15 章从对话循环到构建你自己的 Agent Harness。在线阅读网站：
SylphAI-Inc
★ 4,215AdalFlow
AdalFlow: The library to build & auto-optimize LLM applications.
haris-musa
★ 4,186excel-mcp-server
A Model Context Protocol server for Excel file manipulation
NVIDIA
★ 4,181GenerativeAIExamples
Generative AI reference workflows optimized for accelerated infrastructure and microservice architecture.
UditAkhourii
★ 4,176adhd
ADHD — a skill for coding agents. Tree-of-thought with pruning, built on the Claude & Codex Agent SDK. Fans out parallel divergent thoughts under different cognitive frames, scores, prunes traps, deepens the survivors. The no-brainer skill for creative and interdisciplinary work.
GiovanniPasq
★ 4,166agentic-rag-for-dummies
A modular Agentic RAG built with LangGraph — learn Retrieval-Augmented Generation Agents in minutes.
bragai
★ 4,160bRAG-langchain
Everything you need to know to build your own RAG application