Lightweight local operator agent (browser + OS) runtime for Tauri apps. Connects to an external llama.cpp server via HTTP and exposes a sidecar NDJSON protocol plus a debug CLI.
How to install atomic-agent?
atomicbot-ai/atomic-agent
$git clone https://github.com/atomicbot-ai/atomic-agentInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Install atomic-agent by running `git clone https://github.com/atomicbot-ai/atomic-agent`, then use it for the current task and follow its documentation at https://github.com/atomicbot-ai/atomic-agent.
README.md
| 1 | <div align="center"> |
| 2 | |
| 3 | <img src="assets/logo.svg" alt="Atomic Agent" width="120" /> |
| 4 | |
| 5 | # Atomic Agent |
| 6 | |
| 7 | ### A local-first AI agent that runs on your machine, with local or cloud models. |
| 8 | |
| 9 | Drives your browser, edits files, runs approved commands, and remembers context across sessions. Open source, running on our TurboQuant `llama.cpp` for +30-50% throughput on small local models. |
| 10 | |
| 11 | [](#benchmarks) |
| 12 | [](https://github.com/AtomicBot-ai/atomic-agent/actions/workflows/release.yml) |
| 13 | [](https://github.com/AtomicBot-ai/atomic-agent/releases) |
| 14 | [](package.json) |
| 15 | [](LICENSE) |
| 16 | [](https://nodejs.org/) |
| 17 | [](https://www.typescriptlang.org/) |
| 18 |  |
| 19 |  |
| 20 |  |
| 21 |  |
| 22 |  |
| 23 | |
| 24 | **[Quick Install](#quick-install) · [Benchmarks](#benchmarks) · [Why Local-First](#why-local-first) · [Ways to Use It](#ways-to-use-it) · [Docs](#development)** |
| 25 | |
| 26 |  |
| 27 | |
| 28 | </div> |
| 29 | |
| 30 | --- |
| 31 | |
| 32 | A local-first AI agent that runs the control loop and all state on your machine. It drives your desktop: browse, read and edit files, run approved shell commands, inspect documents, remember context across sessions, schedule follow-ups, and call external tools over MCP. 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. |
| 33 | |
| 34 | ## Quick Install |
| 35 | |
| 36 | macOS / Linux: |
| 37 | |
| 38 | ```bash |
| 39 | curl -fsSL https://api.atomicbot.ai/agent-install | sh |
| 40 | ``` |
| 41 | |
| 42 | Windows (PowerShell): |
| 43 | |
| 44 | ```powershell |
| 45 | irm https://raw.githubusercontent.com/AtomicBot-ai/atomic-agent/main/scripts/install.ps1 | iex |
| 46 | ``` |
| 47 | |
| 48 | 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. |
| 49 | |
| 50 | > [!NOTE] |
| 51 | > Developer preview. APIs, commands, config, and behavior are still moving, so pin a release if you need a stable integration point. Current builds: macOS, Linux x64, and Windows x64. |
| 52 | |
| 53 | ### Run |
| 54 | |
| 55 | ```bash |
| 56 | atomic-agent |
| 57 | ``` |
| 58 | |
| 59 | > [!TIP] |
| 60 | > Coming from Hermes or OpenClaw? Run `/import` in the TUI for a one-shot migration: sessions, cron jobs, and optionally your provider keys. |
| 61 | |
| 62 | ### Troubleshooting |
| 63 | |
| 64 | If something isn't working: |
| 65 | |
| 66 | 1. Copy your error logs and system specs. |
| 67 | 2. Open an issue on [GitHub](https://github.com/AtomicBot-ai/atomic-agent/issues). |
| 68 | 3. Or ask for help in our [Discord](https://discord.com/invite/Us7qXtDGw). |
| 69 | |
| 70 | ## Benchmarks |
| 71 | |
| 72 | 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. |
| 73 | |
| 74 |  |
| 75 | |
| 76 | | Metric | Atomic Agent | Hermes | |
| 77 | |---|---|---| |
| 78 | | **Accuracy** | **37/53 = 69.8%** | 31/53 = 58.5% | |
| 79 | | Avg wall / task | **~217 s** | ~351 s | |
| 80 | | Head-to-head wins | **+15 atomic-only** | +9 Herm |
Related
6 picksType
- langchain-mcp-adaptersMake Anthropic Model Context Protocol (MCP) tools compatible with LangChain and LangGraph agents.Jul 2026
- mcporterTypeScript runtime and CLI for connecting to configured Model Context Protocol servers.Jul 2026
- mcp-proxyA MCP server which proxies requests to a remote MCP server over streamable HTTP or SSE.Jul 2026
- mcp-atlassianThe Model Context Protocol (MCP) Atlassian integration is an open-source implementation that bridges Atlassian products (Jira and Confluence) with AI language models following Anthropic's MCP specification.Jul 2026
- open-webuiOpen WebUIJul 2026
- rulesyncUnified AI rules management CLI tool that generates configuration files for various AI development toolsJul 2026
