How to use Open Jet: what you can do with it

3 use cases

• Run a coding agent fully offline on your own GPU

  Install OpenJet with pipx, let setup pick a model for your hardware, and start coding offline.

  • REPO L-Forster/open-jet
  • Software and DevOps
  • Intermediate
  View prompt

  Install L-Forster/open-jet with pipx, run openjet setup for this machine's GPU, then use openjet in <repo> to <task>. Tell me which model and engine it chose and why.

  Share Email me this

• Let Codex plan while a local model does the edits (Slipstream)

  Connect your ChatGPT Codex subscription or OpenRouter as the planner and let OpenJet's local model do the work.

  • REPO L-Forster/open-jet
  • Codex
  • Software and DevOps
  • Intermediate
  View prompt

  Set up L-Forster/open-jet in Slipstream mode with my Codex subscription as planner and the local model as worker, then do <task> in <repo> and report tokens used by the planner.

  Share Email me this

• Use your existing Ollama or LM Studio models in OpenJet

  Install the cloud extra and add a model profile pointing at your own OpenAI-compatible server.

  • REPO L-Forster/open-jet
  • Software and DevOps
  • Beginner
  View prompt

  Configure L-Forster/open-jet to use my Ollama model <model> through a model_profiles entry in config.yaml, select it with /model, and run <task> in <repo>.

  Share Email me this

Quick start with Open Jet

1. Check you have what it needs: Linux with an NVIDIA RTX 30, 40 or 50 GPU with 24 GB+ and CUDA 12+ for the megakernel; other hardware uses llama.cpp; Recommended: 14 GB+ VRAM or Apple silicon with 24 GB+; CPU-only works; pipx.
2. Open L-Forster/open-jet on GitHub and read the README and license.
3. Run pipx install open-jet
4. Run openjet setup and accept the recommended model (or openjet setup --yes)
5. On an RTX 3090, 4090 or 5090, choose Qwen3.8 27B Q4_K_M MTP so it builds the megakernel
6. Start the agent with openjet in your repo

These steps come from our top use case, Run a coding agent fully offline on your own GPU, which also has a copy-paste agent prompt.

Using the Deduped MCP, get the setup steps for L-Forster/open-jet

claude mcp add --transport http deduped https://dedupedai.com/mcp

Best AI repos for Software and DevOps

About this repo

• Who it is forDevelopers with a capable GPU or Apple silicon who want a coding agent that works offline and costs nothing per token.
• Why it is hot126 stars, talked about in 3 AI sources we track
• LanguagePython
• Sourcegithub.com/L-Forster/open-jet · Back to Hot repos

Requirements

• Linux with an NVIDIA RTX 30, 40 or 50 GPU with 24 GB+ and CUDA 12+ for the megakernel; other hardware uses llama.cpp
• Recommended: 14 GB+ VRAM or Apple silicon with 24 GB+; CPU-only works
• pipx

Related repos

• Trended earlier REPO ollama/ollama Ollama Ollama runs open models such as Gemma, Qwen, DeepSeek, Kimi and gpt-oss locally or in the cloud, with a CLI, a local REST API and official Python and JavaScript libraries.
• Trended earlier REPO nightly-labs/openbot Openbot OpenBot is a local-first desktop app and optional always-on server for running persistent AI coding and assistant agents, each with its own workspace, queue, and conversation.
• Trended earlier REPO mudler/LocalAI LocalAI LocalAI is an open-source AI engine that runs LLMs, vision, voice, image and video models on any hardware, with no GPU required. Each backend (llama.cpp, vLLM, whisper.cpp, stable-diffusion, MLX and more) is pulled only when a model needs it, and every backend sits behind drop-in OpenAI, Anthropic and ElevenLabs compatible APIs, with multi-user auth, quotas and built-in agents with tools, RAG and MCP.