Atomic Agent
A local-first AI operator for your browser, files, shell, and Git
Atomic Agent is an open-source, local-first AI agent that runs on your own machine and can act through your browser, filesystem, shell, and Git. It uses local models by default, keeps sessions on disk, and pauses for approval on risky actions.
Agenticness = how independently a tool can take action, scored across 9 dimensions. Scored independently by David Kooi, Skylark Creations — see full rubric → Last re-evaluated 10 September 2026.
Is this your tool? Claim this listing to manage your content and analytics.
Ask about Atomic Agent
Get answers based on Atomic Agent's actual documentation
Try asking:
About
Atomic Agent is a general-purpose local computer-use agent for people who want an AI assistant to take actions on their own machine rather than send tasks to a hosted service. It can work across a real browser, local files and folders, the command...
This is meaningfully agentic software: it follows a repeated plan-act-observe loop, can use several local tools in a task, and continues until it finishes or you stop it. Atomic Agent says it runs browser, file, and shell actions in parallel when...
Handles domain-specific workflows independently with dynamic replanning.
Dimension Breakdown
Categories
Ask about Atomic Agent
Try asking:
- Free / open source — full functionality available at no cost.
When Atomic Agent changes its pricing, we catch it the next morning
We recrawl every tool in this directory daily. AI Insider is the 3-minute brief on what actually changed — pricing, features, score moves on our 36-point rubric — often before any press coverage. Sent daily. Skipped when nothing happened.