用角色扮演的方式编排多个自主 AI 智能体协作完成复杂任务，让每个智能体各司其职、像团队一样配合干活。
一份面向 AI Agent 开发与大模型求职的系统指南，覆盖上下文工程、高级 RAG、MCP、Agentic RL 和 LangGraph 实战，并附 1.2 万+ 面试题。
Python SDK，用于监控 AI 智能体运行、追踪 LLM 调用成本并做基准评测，兼容 CrewAI、LangChain、AutoGen 等主流智能体框架。
为 AI Agent 提供持久化长期记忆的 MCP 服务，支持 LangGraph、CrewAI、AutoGen 和 Claude，通过 REST API、知识图谱和自主整合让智能体跨会话记住上下文。
一句话就能拉起一支 AI 专家团队，用零代码 YAML 编排多智能体协作，几分钟产出完整方案并自动核验验收结果。
汇总多智能体领域优质论文的资源清单，覆盖 AutoGen、CrewAI、LangGraph 等主流协作框架，方便快速跟进研究进展与选型参考。
What's Changed Features - Make gpt-6-luna crewAI's default model everywhere - Read spreadsheet URLs in an agent's input with tools over every row - Tag eval usage spans w
… functionality to read spreadsheets for agents in crewai-files. - Scaffold and load standalone agent projects. Documentation - Update RagTool description for better parsi
… Agent sessions. - Ask for a missing API key when crewai run starts. - Record the error class when crewai run cannot load a project. - Name the apps CrewAI AMP cannot res
…LLM catalog PR before version bump - Record where crewai run stops before kickoff - Add crewai skill search to list the organization's skills - Pass crewai run --inputs t
What's Changed Features - Add crewai skill search to list the organization's skills - Pass crewai run --inputs to a Python flow - Add deploy create --zip and print the co
…p objects out of association properties ( 4467) - crewai : stop the dict walk leaking credentials onto spans ( 4465) [main be498301c] bump: version 0.62.3 → 0.62.4 66 fil