OpenJet is a terminal-based AI coding assistant that sets up your local LLM stack and keeps file editing, shell execution, and session recovery on your own hardware.

Why use OpenJet instead of a cloud coding assistant?

OpenJet gives you a private, local coding workflow with zero API bills and zero cloud dependency on the main path.

OpenJet detects your hardware, provisions or reuses the backend, configures GPU offload, and gets a local coding model ready to use from the terminal.

Code with a Local LLM in seconds.

Name: OpenJet
Author: OpenJet

Zero API bills. Zero configuration hell.
OpenJet is a terminal-based AI coding assistant that sets up your local LLM stack in seconds. Edit files, run shell commands, and resume coding sessions on your own hardware, safely and completely offline.

GitHub repo Read the docs

100% Private • Auto-Setup • Zero API Bills • Terminal UI

Install and launch

$ git clone https://github.com/l-forster/open-jet.git
$ cd open-jet
$ ./install.sh
$ open-jet --setup
$ open-jet

What it does

From a blank terminal to an autonomous, local coding agent in under a minute.

OpenJet keeps model hosting, file editing, shell execution, and session recovery inside a single, unified TUI.

One-command setup

Run setup, let OpenJet configure the local stack, and get into the coding session without manual runtime assembly.

Private coding agent

Read files, write code, and work against your own codebase locally instead of shipping it to a hosted API.

Approved shell execution

Run tests, builds, and repo commands from the same workflow while keeping command execution behind approval.

Session recovery

Close the terminal and come back later without throwing away the session and starting from scratch again.

The setup engine

Hardware detection that actually works.

OpenJet handles the heavy lifting of running local AI so you do not have to. It detects your machine, provisions the backend, and applies the right settings so the coding session is fast and stable.

Auto-detects Apple Silicon, CUDA, or CPU-only setups to maximize GPU offload

Reuses your existing `llama-server` binary when you already have one

Downloads, builds, and provisions `llama.cpp` entirely from scratch if you do not

Automatically pulls recommended coding `.gguf` models, or lets you bring your own

For companies

Need a version of OpenJet your legal and security teams can sign off on?

We offer commercial terms for organisations that want vendor support, security paperwork, and a cleaner path through procurement.

Open enterprise page

Commercial terms

Structured for internal legal review and company-wide use.

Security paperwork

Includes a security attestation document for internal review.

Support

Email support with a 48 hour response target.

Simple pricing

$200/mo per team or $500/mo unlimited, with annual billing available.

Join the OpenJet Discord for setup help and model discussion.

Join Discord