Why a terminal
Why an agentic terminal
Your builds, tests and git already run in the terminal. So that is where we put the agents.
In Mel, a team of agents reads your project, runs commands, edits files and checks the result. You set the approvals. A step that cannot be undone always asks.
Mel works with Claude, GPT, Gemini, DeepSeek, Qwen and more, in one app. It is free with your own key on Mac, Windows and Linux, and it runs in VS Code too.