AI 智慧代理是用大型語言模型決定下一步要做什麼的程式：它會呼叫瀏覽器、程式碼直譯器或 API 等工具，反覆執行，直到任務完成。這裡的專案既有用來打造自己代理的框架，也有能寫程式、瀏覽網頁或執行業務流程的現成代理。
比較時看三點：能用哪些模型——只支援一家服務商，還是任何相容 OpenAI 介面的端點（包括本地模型）；如何限制代理能做的事——沙箱、核准步驟、權限清單；以及它能否在步驟之間、工作階段之間保留記憶。會執行程式碼或命令列的代理應該在沙箱中執行，給它存取你電腦的權限前先確認這一點。
De-AI writing skill for any Agent Skills-compatible agent (77+ via the Skills CLI), with native plugins for Claude Code, Codex, Grok Build, and Antigravity. Narrative-architecture repair for fiction, venue-matched rules for professional prose. Based on StoryScope (arXiv:2604.03136).
Let Skills Evolve Collectively with Agentic Evolver
Paw Work - selection-first web agent for Chrome: select on the live page, describe the outcome, take away an editable office file. BYOK, sandboxed, no server.
Modular Python framework for AI agents and workflows with chain-of-thought reasoning, tools, and memory.
🧠 Make your agents learn from experience. Now available as a hosted solution at kayba.ai
Build, run and scale AI agents like API and microservices
Atomic Agent is a local-first AI agent. Runs open-weight models on your own machine via llama.cpp.
AingDesk是一款简单好用的AI助手，支持知识库、模型API、分享、联网搜索、智能体，它还在飞快成长中。 AingDesk is a simple and easy-to-use AI assistant that supports knowledge bases, model APIs, sharing, internet search, and intelligent agents. It is still growing rapidly.
Open-source Grok Bot alternative. Choose your own model and sandbox.
🥂 Gracefully face hCaptcha challenge with multimodal large language model.
Vibe-Research: Your Personal Trading Research Agent · A股/美股/港股 的个人投研 Agent：每日复盘、资讯雷达、个股数据、板块中心、我的持仓、研究记录、回测。Vibe-Research 把数据和功能配齐，由你自己的 Agent 驱动投资研究。基于开源的 Codex Harness 打造。
A new SOTA for RAG — an original retrieval architecture and an open-source knowledge base for humans and agents.
An open coding agent for your terminal, built by a community collective rather than a company. Bring your own model, keep your code on your machine, and owe nothing to anyone.
China Unicom's Yuanjing Wanwu Agent Platform is an enterprise-grade, multi-tenant AI agent development platform. It helps users build applications such as intelligent agents, workflows, and rag, and also supports model management. The platform features a developer-friendly license, and we welcome all developers to build upon the platform.
Fulling is an AI-powered Full-stack Engineer Agent. Built with Next.js, Claude, shadcn/ui, and PostgreSQL. Use kubernetes as infra.
SDG is a specialized framework designed to generate high-quality structured tabular data.
Seamlessly integrate LLMs as Python functions
Open source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.
agentUniverse is a LLM multi-agent framework that allows developers to easily build multi-agent applications.
Fast, local-first web content extraction for LLMs. Scrape, crawl, extract structured data — all from Rust. CLI, REST API, and MCP server.
VCP 部署在 AI 模型 API 与前端应用之间，是面向AGI OS开发和探索的工业级基建示范项目。通过统一指令协议、多层级持久化记忆、分布式插件引擎及多 Agent 协作框架，将原本“无状态、无记忆、无工具调用能力”的大语言模型，彻底改造成拥有永久自我意识、物理世界操作权及群体协作智能的完整智能体系统。
The Fable Workflow: how Claude Fable 5 worked, distilled into skills any model can run, with the eval that keeps it honest. Think / act / prove.
A lightweight framework for building LLM-based agents
AI computer use powered by open source LLMs and E2B Desktop Sandbox