Desktop appCommunication and collaboration
Atomic-Chat
Run open-weight models on the desktop and expose them through a local API.
- Stars
- 1,079
- Forks
- 113
- Updated
- Updated Jul 14, 2026
Run open-weight models on the desktop and expose them through a local API.
Atomic Chat is a desktop application for running open-weight language models locally on macOS, Windows, and Linux. Users can load models, chat through the app, and choose among supported inference engines, while an OpenAI-compatible server on localhost lets agents, CLIs, IDE extensions, and other applications reuse the same model. Hardware acceleration and model formats vary by platform; for example, the documented Linux build currently runs GGUF models only.
Resource types
Use cases
Operating systems
Run local language models through a chat interface or compatible API.
Transcribe meetings locally and create summaries with a local or chosen AI provider.
Runtime
Audience
Public GitHub facts last synced Jul 14, 2026.
Manage multiple inboxes, mail rules, snoozing, and scheduled sending.
Set up and manage a local or remote Hermes Agent from a desktop app.