A multi-model agentic terminal for planning, coding, testing, and shipping.
Mel is a desktop terminal and VS Code extension that lets AI agents read projects, run commands, edit files, and verify results. It supports multiple model providers, configurable approvals, project memory, MCP, SSH, and an API for starting runs from your own tools.
Agenticness = how independently a tool can take action, scored across 9 dimensions. Scored independently by David Kooi, Skylark Creations — see full rubric → Last re-evaluated 7 November 2026.
Ask about Mel
Get answers based on Mel's actual documentation
Try asking:
About
Mel is an agentic terminal for developers who want AI to carry out software work from inside the command-line environment. It combines a terminal-based workspace with AI agents that can inspect a project, plan a task, run shell commands, modify...
Mel is meaningfully agentic rather than a chat-only coding assistant: according to its documentation, agents can work through multi-step tasks, execute commands, edit local project files, use SSH to work on servers, and verify their own output....
Proposes and executes multi-step plans with your approval.
Dimension Breakdown
Categories
Ask about Mel
Try asking:
- Free: Download Mel and use the AI agent with your own provider key; provider usage charges apply.
- Pro ($20/mo): Includes hosted credits across supported model providers.
- Max ($200/mo): Includes hosted credits across supported model providers.
- Business ($50/seat/mo): Available from two seats; includes shared hosted-AI credits, one invoice, shared agents, rules, settings, and recommended connectors. Business workspaces use US model providers only.
When Mel changes its pricing, we catch it the next morning
We recrawl every tool in this directory daily. AI Insider is the 3-minute brief on what actually changed — pricing, features, score moves on our 36-point rubric — often before any press coverage. Sent daily. Skipped when nothing happened.