by catlog22 · MCP Server · ★ 566
Maestro-Flow 意图驱动的多智能体工作流编排框架 说出你要做什么,Maestro 自动规划、调度、执行、验证。 简体中文 | English 大多数 AI 编程工具只能让一个 Agent 做一件事。 Maestro-Flow 让多个 Agent 协同完成从头脑风暴到部署上线的全流程 — 自适应决策引擎根据实际结果动态调整策略,知识图谱将每次执行的经验自动积累到下一次。 核心能力 自适应编排 — Ralph v2 引擎读取项目状态,将自然语言意图分类到 40+ 种命令链,在关键节点根据实际执行结果动态决策:继续、回退、还是插入修复循环。不写 YAML,不配置管线。 跨后端调度 — 同一工作流中混用 Claude、Codex、Gemini、Qwen、OpenCode,四种编排模式按需组合:Delegate(异步委派)、Team(角色协作)、Wave(依赖并行)、Swarm(蚁群探索)。 知识自增强 — Agent 执行中发现的模式、陷阱、决策,自动持久化为 Spec 和 Knowhow。Hook 系统将相关知识注入后续 Agent 的提示词 — 项目越用越聪明。 长周期自校正 — Odyssey 系列命令运行数小时级的自主循环,每个检查点自适应调整策略,直到满足验收标准。 安装 需要 Node.js ≥ 18 和 Claude...
| Stars | 566 |
| Forks | 68 |
| Language | TypeScript |
| Category | MCP Server |
| Quality Score | 36.75/100 |
| Open Issues | 2 |
| Last Updated | 2026-10-15 |
| Created | 2026-03-17 |
| Platforms | claude-code, cli, codex, gemini, mcp, node |
| Est. Tokens | ~1181k |
These tools work well together with maestro-flow for enhanced workflows:
Explore other popular mcp server tools:
maestro-flow is Intent-driven workflow orchestration for multi-agent AI development — adaptive lifecycle engine, self-reinforcing knowledge graph, and visual dashboard for Claude Code, Gemini, Codex & more. It is categorized as a MCP Server with 566 GitHub stars.
maestro-flow is primarily written in TypeScript. It covers topics such as ai-agents, claude-code, cli.
You can find installation instructions and usage details in the maestro-flow GitHub repository at github.com/catlog22/maestro-flow. The project has 566 stars and 68 forks, indicating an active community.