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。
A lightweight, rollbackable, and visual Long-Term Memory Server for MCP Agents. Say goodbye to Vector RAG and amnesia. Empower your AI with persistent, graph-like structured memory across any model, session, or tool. Drop-in replacement for OpenClaw.
Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Includes MLX Core macOS app with chat, agent mode, and tool calling.
86 product management skills from Lenny's Podcast for Claude Code and AI agents. Hiring, user research, strategy, shipping, and more.
Daily updated LLM papers. 每日更新 LLM 相关的论文，欢迎订阅 👏 喜欢的话动动你的小手 🌟 一个
Native iPhone app for your Hermes agent
《动手学 Pi》：沿 15 个真实 checkpoint 从零构建 Pi-style Agent
Large Language Model based Multi-Agents: A Survey of Progress and Challenges (In IJCAI 2024)
LuaN1aoAgent is a fully autonomous AI-driven penetration testing agent powered by graph-based cognitive reasoning.
LLM-compiled knowledge bases for any AI agent. Parallel multi-agent research, thesis-driven investigation, source ingestion, wiki compilation, querying, and artifact generation.
The SmythOS Runtime Environment (SRE) is an open-source, cloud-native runtime for agentic AI. Secure, modular, and production-ready, it lets developers build, run, and manage intelligent agents across local, cloud, and edge environments.
Continuously sync your AI setups with one command. Codebase tailor suited agent skills, MCPs and config files for Claude Code, Cursor, and Codex.
One Query. All Search Skill. 聚合 Gemini、Grok、豆包、元宝等平台原生 AI 搜索能力，免费获取科技趋势、行业舆情、热点追踪、旅行规划、日常问题统一接进自己的 Agent 与工作流，指定链接免费爬取
A set of tools that gives agents powerful capabilities.
AttackGen is a cybersecurity incident response testing tool that leverages the power of large language models and the comprehensive MITRE ATT&CK framework. The tool generates tailored incident response scenarios based on user-selected threat actor groups and your organisation's details.
Helping Ethical Hackers use LLMs in 50 Lines of Code or less..
Reverse engineered Windows Copilot into an OpenAI-compatible API. Access GPT-4 and GPT-5 models through a simple REST interface without API keys or billing.
Empryo issue tracker + SoulForge (v2). Empryo is the graph-powered AI coding agent that edits symbols, not strings: AST surgery, full LSP, a live code genome. Get it at https://empryo.com
YAML-native agent workflow execution engine, written in Rust
Hexabot v3 is an AI workflow automation platform, combining workflows, actions, agents, and conversational channels in one runtime.
LightAgent: Lightweight Python framework for OpenAI-compatible agents with tools, memory, guardrails, tracing, lifecycle hooks, multi-agent collaboration, and workflows.
An autonomous agent that takes work, does work, gets paid, and gets better at it.
Multi-Agent System Framework For Complex Tasks
600 行 TypeScript 写成的超级迷你版 pi，让你轻松从 0 写出属于你的 pi-agent
Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.