Mel – the agentic terminal
The AI terminal for teams.
Orchestration
One lead. A team of agents.
Orchestration in Mel runs a team of AI agents on one task. A lead agent splits the work, starts an agent for each part in its own pane, shares memory between them, then integrates and verifies the result.
Orchestration is part of Mel's AI agent — free on your own provider key — 1,500 hosted-AI credits a month on Pro. The terminal is free.
A team of Mel agents
The lead starts Mel agents on the models you choose, each in its own pane, coordinating through shared project memory. Model failures fall back across providers automatically.
A team of CLI agents
Prefer your installed CLI agents? The lead drives Claude Code and Codex in panes — launching them non-interactively and following each to completion.
The flow
Split, run in parallel, integrate.
- 01Decompose
The lead breaks the goal into independent subtasks, each owning different files.
- 02Start the team
Each subtask gets its own agent in its own pane — running in parallel.
- 03Share memory
The agents coordinate through a shared project memory so nothing conflicts.
- 04Integrate
The lead reviews each result, wires it together, and runs the build to verify.
Get started
Build with a team.
The Mel terminal is free to download, no account needed. The AI agent is free on your own provider key — 1,500 hosted-AI credits a month on Pro.