L-Forster

Open Jet

Name: Open Jet
Author: L-Forster

AI community

SOURCE https://github.com/L-Forster/open-jet

Description

A terminal coding agent, and a Python SDK for embedding on-device models in your own apps.

Installation

This entry records only its repository, not the path inside it, so there is no exact command to give. Open the source below and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

README

OpenJet

![Stars](https://img.shields.io/github/stars/L-Forster/open-jet) ![License](https://img.shields.io/github/license/L-Forster/open-jet) ![Qwen3.6-27B Terminal-Bench 2.0](https://img.shields.io/badge/Qwen3.6--27B%20Terminal--Bench%202.0-59.3-blue)

OpenJet self-hosted local AI coding agent running in a terminal

The self-hosted AI coding agent for local LLMs

Use Ollama, LM Studio, or llama.cpp — or let OpenJet provision and host the right GGUF model for your hardware.

A private, offline coding assistant, hardware-aware local inference host, and Python SDK for embedding on-device models in your own applications.

RTX 3090 + Qwen 27B: 33 tok/s -> 70 tok/s with MTP. Open source.

Discord

OpenJet is an open-source local AI coding agent that reads and edits files, runs approved shell commands, uses tools, and keeps sessions on your machine. Connect an existing local LLM server or let OpenJet download, configure, and serve a model itself—without requiring an OpenJet account, subscription, or hosted API.

Local AI coding agent for Ollama, LM Studio, and llama.cpp

OpenJet does not make you rebuild your local LLM setup. Use the server you already run, or let OpenJet provision the complete stack for you.

You have	How OpenJet uses it
Nothing installed yet	Profiles your hardware, selects and downloads a GGUF, provisions `llama-server`, and starts the agent
Ollama	Connects to Ollama's local OpenAI-compatible endpoint
LM Studio	Connects to the local server exposed by LM Studio
llama.cpp + a GGUF	Reuses your model and `llama-server`, with native lifecycle and