L-Forster/open-jet

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.

1 best points · 0 comments · 1 Hacker News post · 137 GitHub stars · View on GitHub

Hacker News discussions

• Show HN: OpenJet – An offline agent harness for memory-constrained edge hardware (1 points, 0 comments, by lforster, 2026-03-15)