FAQ

Is my data sent to the cloud?

No. The agent loop, the model, and your data run on your own machine by default. Cloud providers are used only if you deliberately configure them.

What does it cost to run?

There’s no token bill. You bring your own llama-server (or let the CLI manage one), so the work runs where you do — the meter stops at zero.

What platforms are supported?

atomic-agent is in Developer Preview. macOS is supported today; Linux and Windows are coming soon.

What model does it use?

Any model your local llama-server serves. The published GAIA Level 1 benchmark was run on the same model and hardware as Hermes for a fair head-to-head comparison.

How does it compare to Hermes?

On GAIA Level 1 (53 tasks, same hardware and same model), atomic-agent scored 69.8% versus Hermes’ 58.5% — +11.3 percentage points more accurate and about 1.6× faster per task.

Is it really open source?

Yes — released under the MIT license. Open weights, open source, open traces: software you can understand all the way down. The code lives on GitHub.

Can I extend it?

Yes. Connect external tools through MCP, teach it workflows with skills, and drive it remotely from Telegram.