Automated README summary
Automatically summarized from the README on 19 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A companion CLI and HTTP service that searches Meilisearch and uses Jev to judge whether each top hit matches a yes/no question, splitting accepted hits from a review queue. For developers filtering search results semantically.
How it uses Jev
For each top hit (at most 20 via CLI, 100 via HTTP), the text in the chosen field is sent to Jev with the user's yes/no question. Jev's verdict is routed to yes, no, review, or failure using a default 0.8 threshold; yes stays in hits, review and failure go to review.
Primitives:choice
Technique worth stealing
Route Jev verdicts into yes/no/review/failure buckets with a threshold, sending empty or oversized input to review without a provider call.
Try it
Run python3 -m examples.route_matrix for an offline demo, or the CLI with MEILI_API_KEY and JEV_API_KEY set.
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 material0.84
- Shows a System One patternunclear0.48
- Describes handling uncertaintynot found in the excerpt0.07
- Reports measured numbersnot found in the excerpt0.05
- Is a runnable toolFound in material0.96
- Top-10 learning shortlist signalnot found in the excerpt0.36
- Is a replica of the modelnot found in the excerpt0.04
- Solves a common problem (0–2)score on a 0–2 scale1.25 / 2
- About JevFound in material0.98
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 19 Oct 2026.