by L-Forster · Codex Skill · ★ 68
An offline coding agent for local models. One command sets up the best model your GPU can run, and on 24 GB+ RTX 30/40/50-series cards Qwen3.8-27B runs up to 1.9x faster than llama.cpp.
| Stars | 68 |
| Forks | 6 |
| Language | Python |
| Category | Codex Skill |
| License | AGPL-3.0 |
| Quality Score | 39.25/100 |
| Open Issues | 1 |
| Last Updated | 2026-10-11 |
| Created | 2026-02-16 |
| Platforms | claude-code, codex, python |
| Est. Tokens | ~105k |
These tools work well together with open-jet for enhanced workflows:
Explore other popular codex skill tools:
open-jet is An offline coding agent for local models. One command sets up the best model your GPU can run, and on 24 GB+ RTX 30/40/50-series cards Qwen3.8-27B runs up to 1.9x faster than llama.cpp.. It is categorized as a Codex Skill with 68 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 68 stars and 6 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.