共 4 条相关资源。
基于图（状态机）的 Agent 编排框架，擅长多 Agent 协作、循环与人工介入流程，是 LangChain 官方推荐的复杂 Agent 生产方案。Graph-based agent orchestration from the LangChain team. Ideal for multi-agent collaboration, loops and human-in-the-loop workflows in production.
TypeScript 全栈 Agent 框架：Agent、工作流、工具、记忆、RAG、评估一体化，与 Next.js 生态深度集成，前端团队做 AI 应用的顺手选择。A TypeScript-first agent framework with agents, workflows, tools, memory, RAG and evals integrated — a natural fit for Next.js teams.
号称「100 行」的极简 Agent 工作流框架：只抽象节点与共享存储两个概念，其余全部交给提示词，配套大量「从零实现 XX Agent」教程，极适合学习原理。A minimalist agent workflow framework in ~100 lines: only nodes and shared store abstractions, plus tons of build-from-scratch tutorials.
可自托管的工作流自动化平台，内置大量应用集成节点与 AI Agent 能力，是把 Agent 接入真实业务系统的胶水层。Self-hostable workflow automation with hundreds of integrations and native AI agent nodes — the glue between agents and real business systems.