FAQ
What is Atomic Agent?
Atomic Agent is an open-source, MIT-licensed agent runtime that runs on your own machine. It drives your browser, files, shell, and git through a set of built-in tools, and the language model behind it runs locally through llama.cpp rather than a hosted API, so installing it needs no account, no API key, and no per-token billing. The runtime owns the loop: each inference returns one JSON array of tool calls constrained by a GBNF grammar, the runtime executes them, compresses the results, updates durable state, and asks the model again until the task is done. Conversations, memory, and scheduled tasks persist in SQLite files on your disk instead of growing inside the prompt, risky actions pass through an approval gate before they run, and external tools connect over the Model Context Protocol. It is a Developer Preview, currently v0.5.0, built by AtomicBot, with source at github.com/AtomicBot-ai/atomic-agent.
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 (currently v0.5.0). Builds ship for:
- macOS on Apple Silicon (arm64). There is no Intel Mac build.
- Linux on x64 and arm64.
- Windows on x64.
Running from source requires Node.js 25.7.0 or newer.
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.
Is Atomic Agent backed by NVIDIA?
Atomic Agent is built by AtomicBot, a member of NVIDIA Inception since August 2026. Inception is NVIDIA’s free program for AI startups: it takes no equity and involves no funding, so this is a technical membership, not an investment. It gives us access to NVIDIA developer resources and cloud credits.
Nothing about it changes the runtime. Atomic Agent stays MIT-licensed and local-first, and an NVIDIA GPU is not required — GPU acceleration runs through Vulkan, which covers NVIDIA, AMD, and Intel alike.
Can I extend it?
What hardware do I need?
The binary itself is tiny (~8–9 MB); the model is what needs resources. The default qwen-3.5-4b needs a few GB of disk and enough memory to load. GPU acceleration is used automatically when available — via Vulkan in managed mode, which covers NVIDIA, AMD, and Intel. On macOS the runtime budgets 75% of unified memory; on Linux and Windows it reads your GPU’s VRAM. If a model reports as not fitting, pick a smaller one.
Which model should I use?
qwen-3.5-4b is the default and a good starting point — small, fast, and light on VRAM, which suits tool-routing and repetitive work. The catalog covers the Qwen 3.5, 3.6, and 3.8 generations alongside several Gemma 4 variants, plus a set of embedding models for fuzzy recall.
The catalog moves between releases, so atomic-agent models list is the source of truth for what you can actually pull. Use models pull <id> and models use <id> to switch. See Local models for the full picture.
Do I have to use a local model?
No — local is the default, but not the only option. You can point Atomic Agent at any OpenAI-compatible HTTP endpoint, or configure a cloud provider, if you’d rather. Those paths are opt-in: nothing reaches a cloud model unless you set it up. See Local models.
Where does Atomic Agent store my data?
Everything the agent persists lives under one state directory — by default ~/.atomic-agent, overridable with ATOMIC_AGENT_STATE_DIR. That folder holds your config (config.json), secrets (.env, written with mode 0600), session transcripts, and memory. Treat it like an SSH-key directory: secrets are stored in plaintext locally. See Why local-first for the full layout.
How do I update it?
Re-run the install command from Installation to pull the latest release, or pin a specific version with ATOMIC_AGENT_VERSION. To update the model backend in managed mode, use atomic-agent models update.
How do I uninstall it?
Atomic Agent is a single binary plus its state directory. Delete the atomic-agent binary from your PATH, then remove the state directory (~/.atomic-agent by default) to erase all local data — sessions, memory, config, and secrets. Nothing is installed system-wide.
It’s not working — where do I start?
See the Troubleshooting page. The most common issues are the model server not being healthy (atomic-agent models status) and the wrong GPU being picked (atomic-agent models devices).