Setup & Settings

Hefty works out of the box with sensible defaults. On first run, a guided onboarding wizard walks you through setting up your AI provider and personalizing your experience. All settings can be changed later at any time via the user menu.

Download Hefty

Head to the Downloads page to get the latest installer for your platform (Linux, macOS, Windows, or Docker).

Quick Start

  1. Install Hefty - download the desktop app for your platform from the Downloads page (allow it to run if your OS shows a warning)
  2. Launch Hefty - on first run, the onboarding wizard appears automatically
  3. Follow the wizard - accept the terms, set up your profile (steps vary between admin and non-admin users), connect your AI provider, and customize your agent
  4. Start chatting
Fastest Local Start

Install Ollama, pull a model (ollama pull gemma4:e4b and ollama pull nomic-embed-text), and select Ollama in the setup dialog. Hefty connects automatically.

Explore This Section

First Launch

How to allow Hefty to run on Linux, macOS, and Windows.

Onboarding Wizard

The guided setup that runs on first launch.

Interactive Tutorial

Guided walkthrough of the interface after onboarding.

AI Providers

Ollama, OpenAI-compatible APIs, and the Hefty platform gateway.

AI Settings

LLM, embeddings, and global reasoning settings.

Keyrings

Store secrets in your OS keyring instead of encrypted files.

Remote Access

Configure network access, binding, and headless mode.

Personalizing Hefty

Agent profile, user settings, and personalization options.

Advanced

Environment variables, provider setup details, and the hefty.conf reference.