Overview

The Mel agent is an AI teammate that lives inside your terminal. Start a conversation with ctrl+enter (cmd+enter on macOS), describe what you want, and the agent reads your code, edits files, runs commands, and verifies its own work — all in the same pane where you'd otherwise be typing shell commands yourself.

No API keys to manage

You never paste an API key into Mel. The app talks only to Mel's backend, which holds the provider keys server-side and streams responses from whichever model the request resolves to — Claude, GPT, Gemini, and more, across six providers. Pick a model explicitly or leave the chip on auto and let the router decide per turn. See Models & routing, and Agent streaming if you want the wire-level details.

Tools run on your machine

The backend never touches your files. When the model wants to act, it asks for a tool call — read_file, grep, edit_file, run_command, and friends — and Mel executes it locally, in the working directory of your pane, then sends the result back for the next step. Your code goes to a provider only as the context you and the agent put into the conversation; the tools themselves are local. The full toolset is documented in Tools & approvals.

You stay in control

Reads are low-risk and run freely. Anything that changes state — writing a file, editing a file, running a command — pauses the run on an approval card with Allow, Always allow (for the rest of the conversation, per kind), and Deny. Every applied change renders a diff card with + / - line counts so you can see exactly what happened. When you trust a run, flip on autonomous mode and let it go hands-off.

What a run looks like

A typical turn: the agent reads the relevant files first, posts a live task checklist, works through it — check-offs stream into the transcript as they happen — and finishes with a summary plus an expandable usage report (model used, tokens, tool calls, timing). Long runs can span up to 80 tool round-trips, enough to scaffold and build a whole project from one prompt. See Tasks & the agent lifecycle and The conversation view.

Where to go next