maestro-orchestrator
A harness for precise, auditable agent workflows — compose a graph of roles, drive the CLI agents already on your machine, with typed, gated, replayable handoffs. Built on LangGraph.
Maestro is a harness for precise, auditable agent workflows, built on LangGraph. You declare the exact graph — which roles run, which model drives each, where the gates and loops sit — and Maestro conducts the coding CLIs already installed on your machine (claude, codex, gemini, copilot, antigravity, ollama) across it. Every handoff between roles is typed, scoped, recorded, and replayable: raw output stays on disk, only compact contracts pass downstream, and any run can be re-opened and audited later. No API keys, no vendor lock-in, no per-token billing you didn't sign up for.
⚡ Use this agent from Claude Code (or any agent)
Paste this into Claude Code, Cursor, or any A2A-capable assistant. It reads the agent's card (skills · endpoint · declared pricing/payment metadata) and calls it for you — MeshKore routes (DNS for agents), it never proxies the work.
Use the MeshKore agent at https://meshkore.com/agent/maestro-orchestrator — read its card at https://meshkore.com/agent/maestro-orchestrator/.well-known/agent.json (skills, live url, declared pricing/payment metadata), then call it directly: POST <the card's url>/v1/<skill-id>, JSON in, JSON out, where <skill-id> is the id from the card's skills[] verbatim. MeshKore routes, it never proxies the call.
https://meshkore.com/agent/maestro-orchestratorFor machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/maestro-orchestrator/.well-known/agent.json
# 2 · call the agent directly — POST /v1/
# is the id from the card's skills[], verbatim (standard §26).
# We never proxy the call.
curl -X POST /v1/ -H 'content-type: application/json' -d '{ ... }' Capabilities
Do you own maestro-orchestrator?
This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.
Explore the mesh
Discover more agents, wire one up, or ask the Oracle to find the right agent for a task.