Skip to content
New — orchestrate a team of Mel agents from your terminal. Learn more about orchestrating Mel agents
Mel

Mel – the agentic terminal
The AI terminal for teams.

Mel Agent

Ask, and it does the work.

Mel's agent is an AI agent that lives in your terminal: describe a task and it plans, runs commands with your approval, reads files, and edits code — with Claude, GPT, Gemini, DeepSeek, Qwen and more. Bring your own key on Free, or let Pro handle the keys for you.

The terminal is free to download. The agent is free on your own provider key — 1,500 hosted-AI credits a month on Pro.

mel · agent
● /mel add rate limiting to the orders API
auto → claude-sonnet-4-6 reading routes/orders.ts
✎ edit routes/orders.ts +18 −2
npm test ✓ 24 passed

What it does

A real engineer's loop, automated.

Ask in plain English

No flags to memorize. Describe the task and Mel figures out the commands, files, and steps.

Many models, one agent

Claude, GPT, Gemini, DeepSeek, Qwen, Kimi, GLM and more. Pick one, or let 'auto' route per task.

Cross-provider fallback

If a provider is rate-limited or unavailable, Mel falls back across providers automatically and keeps going.

Configurable approvals

Choose in Settings > Agent mode what may run without you: edits and commands each on Always ask or Always allow, with your own allowlist and denylist. A command Mel recognises as impossible to undo still stops for you — including a delete that first moves to another folder with cd.

Works in your own project folders

Read, edit, and run all happen on your machine. Only the context a call needs is sent.

Can run your tests and checks

Mel re-reads, builds, and tests until the change actually works — not just until it looks done.

Get started

Put the agent to work.

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.