by L-Forster · Codex Skill · ★ 45
OpenJet The local agent for your own GPU Files - tools - shell approval - workflows - local model. OpenJet runs the agent loop locally. No API calls. No code or data upload. RTX 3090 + Qwen 27B: 33 tok/s - 70 tok/s with MTP. Open source. Discord Someone built a local AI agent that runs on your own GPU. OpenJet runs the agent loop locally: No API calls. No code or data upload. RTX 3090 + Qwen 27B: 33 tok/s - 70 tok/s with MTP. Open source. If you are new to local LLMs, OpenJet is the fastest way to get started without spending hours figuring out models, runtimes, and config.
| Stars | 45 |
| Forks | 5 |
| Language | Python |
| Category | Codex Skill |
| License | AGPL-3.0 |
| Quality Score | 69.7664463127525/100 |
| Last Updated | 2026-06-09 |
| Created | 2026-02-16 |
| Platforms | claude-code, codex, python |
| Est. Tokens | ~146k |
Explore other popular codex skill tools:
open-jet is Claude Code for local LLMs. Unified backend, setup, and coding harness for your own models.. It is categorized as a Codex Skill with 45 GitHub stars.
open-jet is primarily written in Python. It covers topics such as agent, ai, ai-agents.
You can find installation instructions and usage details in the open-jet GitHub repository at github.com/L-Forster/open-jet. The project has 45 stars and 5 forks, indicating an active community.
open-jet is released under the AGPL-3.0 license, making it free to use and modify according to the license terms.