#435 · Primary category: AI Coding Assistants
maestro-flow
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
Project last updated:08/24/26
GitHub Stars
537
Forks
66
Contributors
7
License
MIT
Why we included this project
Maestro-Flow is for developers who are tired of one agent doing one thing and want several AI coding tools to carry a single task from idea to deployment. You describe the goal in plain language and it figures out what stage of development you are in, builds a command chain, and hands the work off across Claude Code, Codex, Gemini, and other CLIs, switching between delegation, role-based teams, and parallel waves as the situation changes. Every run feeds what it learns, the patterns and the pitfalls, into a knowledge graph, and hooks inject that back into later prompts, so the project gets smarter the more you use it. For longer jobs it can run autonomous loops with checkpoints, adjusting its strategy until the acceptance criteria pass. If you want orchestrated multi-agent development without writing YAML pipelines, this is a solid, practical option.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
superpowers
An agentic skills framework & software development methodology that works.
ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
skills
Skills for Real Engineers. Straight from my .agents directory.
opencode
The open source coding agent.
andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.