Atomic Chat

Open-source ChatGPT alternative. Run local LLMs or connect cloud models — with full control and privacy.

       

Getting Started · Discord · X / Twitter · Bug Reports

---

Download

macOS (Universal)	Atomic.Chat_1.1.66_universal.dmg
Windows (x64)	Atomic.Chat_1.1.66_x64-setup.exe
iOS	App Store

Download from atomic.chat or GitHub Releases.

---

Features

• 🧠 Local AI Models — download and run LLMs (Llama, Gemma, Qwen, and more) from HuggingFace
• ⚡ Fast Inference Engines — TurboQuant-optimized llama.cpp on all platforms, MLX for Apple Silicon
• ☁️ Cloud Integration — connect to OpenAI, Anthropic, Mistral, Groq, MiniMax, and others
• 🤖 Custom Assistants — create specialized AI assistants for your tasks
• 🔌 OpenAI-Compatible API — local server at localhost:1337 for other applications
• 🔗 Model Context Protocol — MCP integration for agentic capabilities
• 🔒 Privacy First — everything runs locally when you want it to

---

Inference Engines

Atomic Chat ships its own optimized inference stack so models run fast on whatever hardware you have:

• atomic-llama-cpp-turboquant — our fork of llama.cpp with TurboQuant optimizations for faster quantized inference. Works on macOS, Windows, and Linux across CPU and GPU backends.
• MLX-VLM — Apple Silicon-native engine for vision-language models, running directly on the Neural Engine and unified memory. Faster than llama.cpp on M-series chips for supported models.

The local API server at http://localhost:1337/v1 exposes models from both engines through a single OpenAI-compatible endpoint — tools don't need to know which backend is running underneath.

---

Launch With

Atomic Chat runs an OpenAI-compatible server at http://localhost:1337/v1, so any agent, CLI, IDE plugin, or app that speaks the OpenAI API can run on top of your local models — no extra glue needed. Just point its base URL at Atomic Chat and you're done.

A few projects already ship first-class support with their own setup docs:

Tool	What it is	Setup
OpenCode	Open-source TUI coding agent. Add Atomic Chat as a local provider in opencode.json.	Setup guide →
OpenClaude	Open-source coding-agent CLI for cloud and local models. Lists Atomic Chat as a supported provider.	Providers list →
Hermes Workspace	Local-first agent workspace built on Nous Research's Hermes. Uses Atomic Chat as its inference backend.	Repo →
nanoclaw	Containerized agent runtime that calls Atomic Chat as an MCP tool.	Skill guide →

Built something that runs on Atomic Chat? Open a PR and we'll add it here.

---

Build from Source

Prerequisites

• Node.js ≥ 20.0.0
• Yarn ≥ 4.5.3
• Make ≥ 3.81
• Rust (for Tauri)
• (Apple Silicon) MetalToolchain xcodebuild -downloadComponent MetalToolchain

Run with Make

git clone https://github.com/AtomicBot-ai/Atomic-Chat
cd Atomic-Chat
make dev

This handles everything: installs dependencies, builds core components, and launches the app.

Available make targets:

• make dev — full development setup and launch
• make build — production build
• make test — run tests and linting
• make clean — delete everything and start fresh

Manual Commands

yarn install
yarn build:tauri:plugin:api
yarn build:core
yarn build:extensions
yarn dev

---

System Requirements

• macOS: 13.6+ (8GB RAM for 3B models, 16GB for 7B, 32GB for 13B)
• Windows: 10/11 x64 (same RAM recommendations as macOS)
• iOS: 17+ (download from App Store)

---

Troubleshooting

If something isn't working:

1. Copy your error logs and system specs
2. Open an issue on GitHub
3. Or ask for help in our #🆘|atomic-chat-help channel

---

Contributing

Contributions welcome. See CONTRIBUTING.md for details.

   

---

Contact

• Bugs: GitHub Issues
• General Discussion: Discord
• Updates: X / Twitter

---

License

Apache 2.0 — see LICENSE for details.

Acknowledgements

Built on the shoulders of giants:

• Llama.cpp
• MLX-VLM
• Tauri
• Scalar

---

_{© 2026 Atomic Chat · Built with ❤️ · atomic.chat}