Get Started

A second mind you run yourself.

Local, encrypted, model-agnostic. On your machine, your keys, your data — never ours.

Early, and honest about it. For builders who want a second mind they actually control. One command. Requires Python 3.11+. macOS and Linux (Windows: run from source or Docker). Everything installs to ~/.chalie/.

$ curl -fsSL https://chalie.ai/install | bash

Checks dependencies, downloads the latest release, installs the CLI. ~2 minutes.

1. Install → 2. Pick an AI model → 3. Start talking

Start Chalie

chalie                 # Start → http://localhost:31025
chalie --port=9000     # Start on a custom port
chalie stop            # Stop
chalie restart         # Restart
chalie status          # Show running status
chalie update          # Update to latest release
chalie logs            # Follow the log

Complete onboarding

Open http://localhost:31025/on-boarding/ to create an account and configure your AI provider.

Or run with Docker

docker run -d -p 31025:31025 -v ~/.chalie/data:/root/.chalie/app/data chalieai/chalie

Published to Docker Hub for linux/amd64 and linux/arm64 with every release.

AI Provider

Choose your model

Onboarding creates your account. You add your AI model afterward in Brain → Settings → Providers — a short wizard that only asks for what each provider needs.

Ollama

Recommended

Free, private, runs entirely on your machine.

Install Ollama

Download from ollama.ai

Pull a model

ollama pull gemma3:4b

A small model gets you running; larger models reason better. Local means free and private — nothing leaves your machine.

In Brain → Settings → Providers → Add Provider, pick Ollama. Host: http://localhost:11434 — no key needed.

Configuration

That's it, really

Chalie auto-generates secrets and stores all configuration via the web UI. The only runtime option is the port: 

chalie --port=9000     # default: 31025

Voice is off by default and isn't bundled by the installer. Turn it on in Brain → Settings; Chalie installs the voice dependencies and models in the background, and the controls appear once they're ready.

Security

Before going public

Enable HTTPS

Use a reverse proxy (nginx, Caddy, Traefik) to terminate TLS connections.

Use a strong password

Set during initial onboarding. Protects your data and conversations.

Restrict CORS

Update the CORS origin before exposing to a network.

For hackers

Run from source

Clone the repository

git clone https://github.com/chalie-ai/chalie.git && cd chalie

Install dependencies

python3 -m venv .venv && source .venv/bin/activate
pip install -e backend/          # core deps from pyproject.toml

Run & test

./run.sh                         # → http://localhost:31025
cd backend && pytest -m unit -q  # run the unit tests