Maestro documentation
Start with install and quickstart, then learn how Maestro keeps the loop running, what the control center is telling you, and which knobs matter when you need to step back in.
Install
Install the local runtime once, then use the same command in every repo you want to supervise.
npm install -g @olhapi/maestroBootstrap workflow
Setup repo contract once so Maestro can keep making the same handoff decisions while you are elsewhere.
maestro workflow init .Start orchestration
Start the daemon and embedded control center so the queue keeps moving while status, retries, and sessions stay visible.
maestro runRead by the moment you need to step back in
Each section maps to a real operator moment: install, make the first handoff, understand what the loop is doing, then tune or debug it when needed.
Getting Started
Install Maestro, start a local loop, and make the first handoff.
Core Concepts
Understand how Maestro keeps work moving and how to step back in without losing context.
Understand how the local store, MCP bridge, and daemon stay aligned so you can hand work off and still trust the loop.
Control centerUse the embedded dashboard to see whether the loop should keep running or whether a developer needs to step back in.
Workflow configTune how much work Maestro can offload, how aggressively it retries, and which guardrails stay in place through WORKFLOW.md.
Reference
Look up the commands, APIs, and operations details that help you supervise or debug the loop.
Advanced
Use deterministic end-to-end harnesses when you need to verify the full handoff and execution path.
Three common re-entry points
If you already know where the friction is, jump straight to the page that helps you start the loop, read its state, or change how it behaves.
Install and quickstart
Use this when you want the shortest path from install to a loop that keeps working while you move on.
Control center
Use this when Maestro is already running and you need to decide whether to intervene or let it continue.
Workflow config
Use this when the loop is running but you need tighter control over dispatch, retries, or guardrails.