# Atomic Agent ### A local-first AI agent that runs on your machine, with local or cloud models. Drives your browser, edits files, runs approved commands, and remembers context across sessions. Open source, running on our TurboQuant `llama.cpp` so long sessions with small local models fit in less memory. [](#benchmarks) [](https://github.com/AtomicBot-ai/atomic-agent/actions/workflows/release.yml) [](https://github.com/AtomicBot-ai/atomic-agent/releases) [](package.json) [](LICENSE) [](https://nodejs.org/) [](https://www.typescriptlang.org/)      **[Quick Install](#quick-install) · [Uninstall](#uninstall) · [Benchmarks](#benchmarks) · [Why Local-First](#why-local-first) · [Ways to Use It](#ways-to-use-it) · [Docs](#development)** 

A local-first AI agent that runs the control loop and all state on your machine. It works across your machine: browse the web, read and edit files, run approved shell commands, inspect documents, remember context across sessions, schedule follow-ups, and call external tools over MCP. Run it on a local model, a cloud model, or both at once in Fusion mode, where one model plans and a pool of workers executes. Embed it in your own apps over HTTP or a Tauri sidecar. llama.cpp first, so small quantized models stay useful for long, multi-step work on consumer hardware.

Quick Install

macOS / Linux:

curl -fsSL https://atomicagent.io/install | sh

Windows (PowerShell):

irm https://atomicagent.io/install.ps1 | iex

The installer downloads the release archive, verifies the checksum, and installs the CLI plus support assets (grammars/, native prebuilds, and bundled ripgrep). Atomic Agent updates itself in place; after an update the TUI prompts you to restart. Outside the TUI, run atomic-agent update (or atag update) to check for a newer release and re-run the installer in place; atomic-agent update --check probes without installing, and --version <tag> pins a specific release. Only the installed binary can self-update; a dev checkout updates via git, and a Linux package (below) updates with the package manager.

Linux packages

On Debian, Ubuntu, Fedora, RHEL-compatible systems and Arch, Atomic Agent also comes as a package, and the package manager then updates it with the rest of the system. A package carries the same release bundle as the installer, under /usr/lib/atomic-agent, with atomic-agent and atag in /usr/bin. The repository and the rpm packages are signed with the Atomic Chat packages key in packaging/atomic-chat.asc, fingerprint 1047 F119 58C6 442D D472 E497 E4C3 D361 FB7F F123.

Debian, Ubuntu (x86-64, arm64):

curl -fsSL https://atomic-agent-packages.fsn1.your-objectstorage.com/atomic-chat.gpg | sudo tee /usr/share/keyrings/atomic-chat.gpg >/dev/null
echo "deb [signed-by=/usr/share/keyrings/atomic-chat.gpg] https://atomic-agent-packages.fsn1.your-objectstorage.com/deb stable main" \
  | sudo tee /etc/apt/sources.list.d/atomic-agent.list
sudo apt update && sudo apt install atomic-agent

Fedora, RHEL, Rocky, Alma (x86-64, aarch64):

sudo curl -fsSL -o /etc/yum.repos.d/atomic-agent.repo https://atomic-agent-packages.fsn1.your-objectstorage.com/rpm/atomic-agent.repo
sudo dnf install atomic-agent

Arch Linux: yay -S atomic-agent-bin, or any other AUR helper.

Updates come with sudo apt upgrade, sudo dnf upgrade or yay -Syu; on a packaged install atomic-agent update refuses and names the command to use, and the TUI does not offer its in-app update. A copy left by install.sh in ~/.local/bin runs ahead of the package on the usual PATH and keeps its own updates; atomic-agent update names both copies when that happens, and removing the copy hands the command to the package. sudo apt remove atomic-agent, sudo dnf remove atomic-agent or sudo pacman -R atomic-agent-bin removes the program and leaves your data; atomic-agent uninstall then lists only the data. The repository keeps the last ten releases; older ones are on the releases page as .deb and .rpm files. A package states the glibc its binary needs (2.34 today: Debian 12, Ubuntu 22.04, RHEL 9 and newer), and the package manager refuses where the system's is older.

Desktop app

The desktop app is in the same repository as atomic-agent-desktop (on Arch atomic-agent-desktop-bin). It has releases of its own (desktop-vX.Y.Z), carries its own copy of the agent under /opt/Atomic Agent and leaves a packaged or installed atomic-agent alone, so the two can be installed side by side. Once installed it is in the applications menu, and atomic-agent-desktop starts it from a terminal.

Debian, Ubuntu (x86-64, arm64):

curl -fsSL https://atomic-agent-packages.fsn1.your-objectstorage.com/atomic-chat.gpg | sudo tee /usr/share/keyrings/atomic-chat.gpg >/dev/null
echo "deb [signed-by=/usr/share/keyrings/atomic-chat.gpg] https://atomic-agent-packages.fsn1.your-objectstorage.com/deb stable main" \
  | sudo tee /etc/apt/sources.list.d/atomic-agent.list
sudo apt update && sudo apt install atomic-agent-desktop

Fedora, RHEL, Rocky, Alma (x86-64, aarch64):

sudo curl -fsSL -o /etc/yum.repos.d/atomic-agent.repo https://atomic-agent-packages.fsn1.your-objectstorage.com/rpm/atomic-agent.repo
sudo dnf install atomic-agent-desktop

Arch Linux: yay -S atomic-agent-desktop-bin, or any other AUR helper.

Installed as a package, the app is updated with the rest of the system (sudo apt upgrade, sudo dnf upgrade or yay -Syu) and its Settings say so instead of offering an in-app update; the AppImage from the releases page updates itself. sudo apt remove atomic-agent-desktop, sudo dnf remove atomic-agent-desktop or sudo pacman -R atomic-agent-desktop-bin removes the app and leaves your data.

[!NOTE] Developer preview. APIs, commands, config, and behavior are still moving, so pin a release if you need a stable integration point. Current builds: macOS (Apple Silicon), Linux x64 / arm64, and Windows x64. Intel Macs are not supported yet; Windows on ARM runs the x64 build under emulation.

Run

atomic-agent

Both installers also drop a short alias next to the binary, so this is the same thing:

atag

[!TIP] Need a second agent? Press Ctrl+N (or run /window) inside the TUI: it opens a new terminal window with a fresh atomic-agent in the same directory.

[!TIP] Want to go through first-time setup again? Run /onboarding (or /setup) in the TUI, or start it with atomic-agent tui --onboarding. Your providers, keys, sessions and memory are kept.

[!TIP] Coming from another agent? The first run offers to bring your data over: tick the sources it found and the import runs, without overwriting anything already here and without touching the source. What moves depends on the source:

• Claude Code: skills, memory, MCP servers, sessions, and (opt-in) provider keys
• Codex: skills, memory, sessions, and (opt-in) provider keys
• Oh-My-Pi: skills, MCP servers, and sessions
• Pi: skills and sessions
• Hermes: sessions, cron jobs, and (opt-in) provider keys
• OpenClaw: sessions and cron jobs

Later, run /import in the TUI or atomic-agent import <hermes|openclaw|claude-code|codex|pi|oh-my-pi> from the shell.

Uninstall

One command removes everything: the state directory (config, memory, sessions, tasks, traces, downloaded models), the binary and its atag alias, the asset directories beside them, and the PATH line the installer added to your shell rc file:

atomic-agent uninstall

It prints exactly what it will delete, with sizes, and then asks you to type the word uninstall. Nothing is uploaded and nothing is kept; this cannot be undone. Preview it with atomic-agent uninstall --dry-run, keep your data with --keep-data, keep the binary with --keep-binary, leave your shell rc file alone with --keep-path, or skip the prompt in a script with --yes. The same flow is the last entry in the TUI's own menu (Esc → Danger zone, or /uninstall). The desktop app (0.0.3 and later) shares the same ~/.atomic-agent folder. When uninstall finds it, an interactive run asks a separate question before deleting that folder (answer no to remove only the terminal program), and a --yes run keeps the folder and says why; add --include-desktop-data to delete it in a script.

Troubleshooting

If something isn't working:

1. Copy your error logs and system specs.
2. Open an issue on GitHub.
3. Or ask for help in our Discord.

Talk to Us

Building something with Atomic Agent, stuck on setup, or just want to share what you are working on? Grab a slot and talk to the team directly: cal.com/atomicagent/demo. No agenda required. Questions, feedback, feature requests, or a plain hello all count. We read every issue and every Discord message too, but sometimes a 15-minute call beats a week of comments.

Benchmarks

On the public GAIA validation Level 1 split (53 tasks), Atomic Agent and Hermes drove the same local qwen-3.6-35b-a3b (llama-server, UD-Q4_K_XL), with the same step budget and timeout. The only variable is the agent loop.