██████╗██████╗ ██╗ ██╗███████╗████████╗ █████╗ ██╗ ██╔════╝██╔══██╗██║ ██║██╔════╝╚══██╔══╝██╔══██╗██║ ██║ ██████╔╝██║ ██║███████╗ ██║ ███████║██║ ██║ ██╔══██╗██║ ██║╚════██║ ██║ ██╔══██║██║ ╚██████╗██║ ██║╚██████╔╝███████║ ██║ ██║ ██║██║ ╚═════╝╚═╝ ╚═╝ ╚═════╝ ╚══════╝ ╚═╝ ╚═╝ ╚═╝╚═╝
Always on. Always yours. Never in the cloud.
Connect your favorite messaging apps to a local AI — zero subscriptions, zero telemetry.
Built for developers and privacy enthusiasts who want a real AI assistant without giving up control of their data.
All conversations stay on your machine. No data sent to external AI services. No telemetry. No tracking. Ever.
Powered by Ollama — supports llama3.2, tinyllama, phi3, mistral and any other compatible model.
One assistant, four platforms. Telegram, WhatsApp, Discord and Slack — all managed from a single config file.
CrustAI remembers facts about you across conversations using the /remember command and local SQLite storage.
Speech-to-text and text-to-speech support in Portuguese (pt-BR) — works completely offline after setup.
Built-in Fastify REST API for custom integrations. Connect any tool or service to your local AI assistant.
No Docker required. No cloud accounts. Just Node.js and Ollama on your own machine.
Download CrustAI to your machine using Git.
Install all required Node.js packages.
Start the Ollama server and download your preferred AI model. tinyllama works great on modest hardware.
Copy the example config and add your Telegram bot token from @BotFather.
Start the assistant and open your Telegram bot to begin chatting.
Enable only the platforms you use. Each adapter is independently configurable in config.yml.
Full bot integration via @BotFather token
Connect via QR code scan — no business account needed
Full Discord bot with server and channel support
Slack app integration for teams and workspaces
HTTP API always running on localhost:3000
WebSocket voice server with offline STT/TTS
Type these commands directly in any connected messaging platform.
CrustAI was built with privacy as its core principle — not an afterthought.
All conversations processed locally. Nothing leaves your hardware.
Zero calls to OpenAI, Anthropic, Google or any cloud AI service.
No usage tracking, no analytics, no crash reports sent anywhere.
Every line of code is auditable. MIT license — use it however you want.