ReinaMacCredy/maestro
Harness for long-running AI coding agents -- structured memory, cross-feature learning, and plan-approve-execute workflow
Implements a **CLI-first state machine** for multi-agent coordination, with persistent `.maestro/` directories tracking features, plans, tasks, and memory across sessions. Built on a **clean architecture** (domain ports, app layer, infra adapters) that degrades gracefully when optional integrations (beads_rust task sync, beads_viewer dependency graphs, CASS full-text search, MCP Agent Mail handoffs) are unavailable. Provides **5 Claude Code hooks** for automatic context injection, **Dynamic Context Pruning** for budget-aware memory scoring, and **21 bundled skills** guiding agents through discovery→research→planning→approval→execution workflows.
Available on npm.
Stars
23
Forks
3
Language
TypeScript
License
—
Category
Last pushed
Mar 28, 2026
Commits (30d)
0
Dependencies
18
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/ReinaMacCredy/maestro"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
RunMaestro/Maestro
Agent Orchestration Command Center
ComposioHQ/agent-orchestrator
Agentic orchestrator for parallel coding agents — plans tasks, spawns agents, and autonomously...
mindfold-ai/Trellis
All-in-one AI framework & toolkit
supaku/agentfactory
The open-source software factory — multi-agent fleet management for coding agents
kagan-sh/kagan
The Orchestration Layer for AI Coding Agents