Atomic Agent
Atomic Agent is a local-first terminal coding assistant that runs open-weight models through llama.cpp and keeps its control loop and state on the user’s machine. It can browse, work with files and Git, retain memory across sessions, and connect external tools over MCP.
Where it fits
Atomic Agent is listed in AI Agents, Local Inference, Terminal-Friendly. Use its original project documentation to confirm the features and setup for your intended workflow.
Explore agent applications that combine a model with tools and a task loop. Start with the job you want completed, then compare access requirements, human control and how a successful result is checked.
Before you choose
Use these category-level questions when reviewing this resource. They do not assert that this project supports a particular feature.
- Can you define a concrete completed task?
- Which accounts, files or systems can the agent access?
- Can you inspect its work and stop or undo an action?
Sources & project links
About this listing
Imported directory snapshot · 2026-10-26. The description and classification come from the earlier directory, adapted from awesome-ai-agents; current project behavior has not been independently tested.
Pricing, licensing, supported models and hosting requirements may change. Check the original project before installing or paying. Inclusion is not an endorsement or a performance rating.
Historical repository popularity
The old directory displayed 2.7k GitHub stars. Its original observation date is unknown. This is retained as historical context, not a live count or quality score.