Automated README summary
Automatically summarized from the README on 20 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A Jev-style skill router for OmO. A frozen Qwen2.5-0.5B plus a small option-attention head scores the whole skill catalog against the user's prompt, and an OmO extension trims the skill block to the top-K.
How it uses Jev
Jev scores every catalog skill (name: description options) against the user prompt in one forward pass; the extension keeps the top-K skills in the system prompt, preserves explicit $skill:name invocations, and returns the prompt unchanged on any error (fail-open).
Primitives:score
Technique worth stealing
Cache catalog option embeddings once, then train only a small option-attention head over a frozen encoder.
Try it
docker compose up --build -d in server/, then copy extension/jevlike-router.js to ~/.omo/extensions/.
Model judgments from README excerpts
Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.
Models & evaluation dates
- Inclusion gate
jev-1.13.0- Project signals
jev-1.13.0- Category
jev-1.13.0- Pattern tags
jev-1.13.0
Evidence
These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.
- Jev is core to the projectFound in material0.70
- Shows a System One patternnot found in the excerpt0.34
- Describes handling uncertaintyFound in material0.90
- Reports measured numbersunclear0.52
- Is a runnable toolFound in material0.91
- Top-10 learning shortlist signalunclear0.50
- Is a replica of the modelFound in material0.93
- Solves a common problem (0–2)score on a 0–2 scale1.13 / 2
- About JevFound in material0.94
no-judgment band (0.40–0.60)
no-judgment band (0.40–0.60)
The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 20 Sept 2026.