Skip to content
atomic-agent docs

Quickstart

atomic-agent is a local-first operator agent runtime. One inference produces one JSON array of tool calls; the runtime executes those calls, compresses the results, updates durable state, and asks the model for the next move. It runs on your own machine — no cloud, no API key, no token bill.

1. Install

Run the one-line installer:

Terminal window
curl -fsSL https://api.atomicbot.ai/agent-install | sh

This is the same command from the homepage. Nothing leaves your machine — you can inspect the script before you run it.

2. Start a local model

atomic-agent talks to a local llama-server by default. Either point it at a server you already run, or let the CLI manage one for you. See Installation for the full list of requirements.

3. Run it

Terminal window
atomic-agent

Or open the terminal UI scoped to a working directory:

Terminal window
atomic-agent tui --cwd /path/to/work

You’ll land in the TUI with Run · Observe · Manage tabs and a status bar showing your model and health. Type a request at the prompt and press Enter.

What next?

  • Learn the CLI and the keyboard shortcuts.
  • Point it at your models and tune limits in Configuration.
  • Browse what it can actually do under Features.