Agent References
Blogs LLM Powered Autonomous Agents | Lil’Log - Lilian Weng 关于 LLM Agent 的经典综述,覆盖规划、记忆和工具使用。 Function calling | OpenAI API - OpenAI API 关于函数调用和工具调用的官方文档。 Model Context Protocol - MCP 官方文档,关注模型应用如何连接外部工具、数据和上下文。 A2A Protocol - Agent 与 Agent 之间通信和互操作的协议文档。 Equipping agents for the real world with Agent Skills | Anthropic - Anthropic 关于 Agent Skills 的官方博客,介绍能力封装和按需加载的思路。- The Agent Skills Directory Introduction - Agent Client Protocol - Agent Client Protocol 官方入门文档,定义客户端应用与 Agent 之间的标准交互方式。 Codex 应用服务器 | ChatGPT 学习 - Codex App Server 官方文档,介绍如何把 Codex 作为本地服务接入自定义客户端,支持会话、审批和事件流。 企业级 Agent 多智能体架构与选型指南 – 来自 1000+ 行业应用实践积累 - 面向企业级场景的多智能体架构和技术选型经验。 Projects openclaw/openclaw: Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞 NousResearch/hermes-agent: The agent that grows with you bytedance/deer-flow: 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. ultraworkers/claw-code: An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention. openai/codex: Lightweight coding agent that runs in your terminal multica-ai/multica: The open-source managed agents platform. Turn coding agents into real teammates — assign tasks, track progress, compound skills.