ruvnet / ruvllm
Governed neural weight editing and coding model adaptation. Native Rust patches, exact rollback, LoRA, Claude Code routing, and reproducible benchmarks.
Why this job: says: lora; topics: lora
What it does
RuVLLM trains and edits small adapters for open language models, then measures each one against the unchanged base on the same tasks, under a rule written before the results. Every decision to keep or reject an adapter is backed by every raw answer, a paired significance test and a local re-score. The original weights restore byte for byte.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 3 days ago
- Stars
- 13
- +7 this week
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest tag
- gpu-measurements-20261104
- Released 5 days ago
- Built with
- Python
- 55% of the code
Is it looked after?
- Contributors
- 1
- Last 90 days
- Issues
- 0% closed
- 1 still open
- Pull requests
- 11 merged
- 0 waiting
- Releases
- 2
- 2 in the last year
- Contributing guide (opens in new tab)
- Security policy (opens in new tab)
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| wuwangzhang1216 / abliterix | 286 | 5 days ago | AGPL-3.0 | No downloads |
More: languages, topics and project record
Languages
- Python 55%
- JavaScript 22%
- Rust 13%
- HTML 9%
Topics
- agentic-ai
- ai
- ai-governance
- benchmarks
- claude-code
- evals
- gpu
- llm
- lora
- mlx
- model-editing
- model-routing
Project record
- JobFine-tuning
- StatusNew to our list
- Commits18
- Forks1
- Watching1
- CreatedNov 3, 2026
- First seen by usNov 7, 2026
- CheckedNov 8, 2026