Now in open beta — orchestrate a team of Mel agents from your terminal. Learn more

Orchestration

One lead. A team of agents.

Hand Mel a big task and it runs a whole team. A lead agent decomposes the work, spawns workers across panes, shares memory between them, then integrates and verifies — hands-off.

/orchestrate-agent

Workers are Mel agents

The lead spawns worker Mel agents on the models you choose, each in its own pane, coordinating through cross-agent shared memory. Model failures fall back across providers automatically.

/orchestrate-cli

Workers are CLI agents

Prefer your installed CLI agents? The lead drives Claude Code, Codex, and opencode in panes — launching them non-interactively and polling each to completion.

The flow

Decompose, spawn, integrate.

  1. 01
    Decompose

    The lead breaks the goal into independent subtasks, each owning different files.

  2. 02
    Spawn

    Each subtask gets its own worker agent in its own pane — running in parallel.

  3. 03
    Share memory

    Workers coordinate through a shared project memory so nothing conflicts.

  4. 04
    Integrate

    The lead reviews each result, wires it together, and runs the build to verify.

orchestrator · build loyalty rewardsdone
>_Accrual APIworker · api/ordersMel Agent
>_Balance UIworker · app/accountClaude Code
>_Checkoutworker · app/checkoutCodex

Build with a team.

Free, open source, for macOS, Windows, and Linux.