atomic-agent

atomic-agent is an agent framework - Local First Ai Agent. Optimized for Local Ai models. Long context window. Proper tools callings. Runs privately on your device.

Overview

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.

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.

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.

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

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.

The same loop holds up as the local model shrinks. Same GAIA L1 split, Atomic Agent alone:

atomic-agent is open-source, written primarily in TypeScript, with 1,637 GitHub stars under the MIT license. The latest release is v0.1.72 (2026-08-06).

Key capabilities

From the project's documentation:

• Runs on your hardware. Small quantized models run on everyday consumer GPUs and CPUs, no datacenter needed.
• Curated quantized models: hand-picked GGUF quants that keep quality high while fitting real VRAM budgets.
• Managed mode: the CLI downloads, pins, and runs the backend and models for you, no manual llama.cpp setup.
• GBNF tool calls: completions are constrained into a JSON array of tool calls, including the solo case [{...}].
• Profile facts render into ### profile with contextual keyword gating; facts are versioned, with queryable history.
• Notes are stored in SQLite + FTS5, optionally paired with embeddings for hybrid recall.

Install

A quick way to get started (always check the official docs for the latest):

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

How it fits a local-AI stack

atomic-agent runs on your own hardware, so pair it with a model and a GPU sized to your needs. Use the VRAM calculator to pick a model that fits your card, and see what you can run for hardware guidance. Related agent frameworks in the directory:

• "agentic-inbox"
• Agno
• "ai-agents-from-scratch"
• "aider"

Sources

• Source code & docs: AtomicBot-ai/atomic-agent
• Official website: https://atomicagent.io

Stats from GitHub, 2026-08-08.