Linux first · local AI · public source

An AI node.
On a machine you control.

OpenZero brings a model runtime, an operator panel and an OpenAI-compatible API together for builders who want their own AI setup. It is a self-hosted source project: you supply the computer, model and configuration.

The pieces of your setup

Runtime

Run a model

Use the project's supported Ollama and local-model routes. Choose a model that fits your memory, storage and workload. Downloading a model and running it are separate from browsing this website.

Operator panel

See the node

The project documents a Super Panel for runtime health, model controls, configuration and local status. Follow the version-specific instructions for the installation you choose.

Build

Connect a client

An OpenAI-compatible API gives applications and scripts a documented connection route. Configure the client's endpoint and the model actually available on your node.

Start from the current source

  1. Read the README and requirements for the current release.
  2. Use a Linux machine you control and review the installation guide before running scripts.
  3. Get a small model answering locally, then open the documented operator panel.
  4. Review the API guide before connecting your application.
  5. Enable optional voice, browser or automation features individually and review their permissions.
This page is the project directory, not a hosted OpenZero session. Some older repository instructions refer to retired hosted services. Use the current GitHub source and your own runtime; avoid legacy hosted install URLs.

What to consider first

Hardware and operating costs

Local inference uses memory, disk space and electricity. Larger models can need considerably more resources. Begin with a small task and a model that fits your machine.

Where data goes

A local model request can stay on your machine, while optional remote APIs and web tools use external services. Local installation alone does not make every workflow offline.

Maintenance

You operate the runtime, updates and network exposure. Keep the service on its intended interface and follow the project's release and security instructions.

Project issues ↗ · Compare AI routes →