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.
Why this job: says: llama.cpp; topics: llama-cpp, ollama, local-llm, llm-inference, inference, inference-engine
What it does
Context on a 24 GB card: about 120K tokens, or about 234K with openjet setup --long-context (KV cache presets).
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 8 days ago
- Stars
- 139
- +8 this week
- Licence
- AGPL-3.0
- Share-alike, even hosted
- Downloads for
- 3 systems
- Mac, Windows, Linux
- Latest version
- v0.5.4
- Released 10 days ago
- Built with
- Python
- 63% of the code
Is it looked after?
- Contributors
- 5
- Last 90 days
- Issues
- 78% closed
- 2 still open
- Pull requests
- 18 merged
- 0 waiting
- Releases
- 19
- 19 in the last year
- Contributing guide (opens in new tab)
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| xLLM-AI / xllm | 1,618 | today | Apache-2.0 | No downloads |
| wici-ai / inferssd | 364 | today | Apache-2.0 | Mac, Windows |
| pegainfer-project / pegainfer | 738 | yesterday | Apache-2.0 | Linux |
More: download files, languages, topics and project record
Download files, v0.5.4
- Mac4 files, 11 downloads
- Windows6 files, 30 downloads
- Linux8 files, 56 downloads
Languages
- Python 63%
- Cuda 34%
- C++ 2%
- Shell <1%
Topics
- agent
- ai
- ai-agents
- claude-code
- codex
- coding-agent
- cuda
- inference
- inference-engine
- llama-cpp
- llm
- llm-inference
Project record
- JobLocal LLMs
- StatusListed
- Commits397
- Forks16
- Watching0
- Stars in 28 days+54
- CreatedFeb 16, 2026
- First seen by usNov 7, 2026
- CheckedNov 7, 2026