Vibe Coding Discover

AI Frameworks

Atomic-Chat

View on GitHub

Local AI app and inference engine for agents. Run open-weight LLMs locally — private, 100% offline on your computer. Join our Discord: https://discord.com/invite/8wGSsvmg4V

★ 1.7K193 forksTypeScriptCustomAtomicBot-ai

A cross-platform desktop app and inference engine for running open-weight LLMs locally. It exposes an OpenAI-compatible API for agents and other clients, supports MCP servers, and includes llama.cpp and MLX-based backends.

Use Cases

Run open-weight models locally for private chatServe local models through an OpenAI-compatible APIProvide inference for AI agents and coding toolsConnect MCP servers and tools to local modelsSwitch between local inference engines and cloud providers

Built With

Language
TypeScript
Frameworks
llama.cpp · MLX · MLX-VLM · Tauri

Tags

local LLM · inference engine · offline AI · OpenAI-compatible API · desktop app · MCP · Apple Silicon · agent backend