maestro-flow MCP Server
catlog22/maestro-flow
[](https://agentrank-ai.com/tool/catlog22--maestro-flow/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge) 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
claude mcp add agentrank -- npx -y agentrank-mcp-server Overview
catlog22/maestro-flow is a TypeScript tool. 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 Topics: ai-agents, claude-code, cli, codex, gemini, knowledge-graph, mcp, multi-agent, typescript, workflow-orchestration.
Ranked #973 out of 81417 indexed tools.
In the top 2% of all indexed tools.
Ecosystem
Score Breakdown
563 stars → growing community
Last commit 11d ago → recently updated
17/21 issues closed → responsive maintainer
9 contributors → small team
No dependents → no downstream usage
Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →
How to Improve
Matched Queries
From the README
<div align="center"> # 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。** <br/> [简体中文](README.md) | [English](README.en.md) </div> <br/> > 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。 <br/> ## 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、Grok,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 ```bash npm install -g [email protected] maestro install # 交互式选择安装组件 ``` 需要 Node.js ≥ 22.19 和至少一个宿主 CLI:[Claude Code](https://docs.anthropic.com/en/docs/claude-code)(默认)和/或 [Grok Build](https://docs.x.ai/build/overview)。多 Agent 工作流还可选装 Codex CLI、agy CLI。 Grok 一等适配:先装官方 `maRead full README on GitHub →
Get the weekly AgentRank digest
Top movers, new tools, ecosystem insights — straight to your inbox.