Automated README summary
Automatically summarized from the README on 4 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A local-first hybrid RAG system for one person on one machine: upload documents, ask questions, get cited answers. Includes a benchmark lab comparing traditional and hybrid pipelines over 11 scenarios with an independent LLM judge.
How it uses Jev
A local 0.8B Jev-style model makes typed, calibrated decisions: gates escalation based on reranked passage scores, decomposes hard questions, selects best of two candidates, and verifies citations. It never generates prose; the cloud LLM writes the answer.
Primitives:choicescorenoul
Technique worth stealing
Use a small local decision model to gate expensive cloud LLM calls and verify citations, keeping most processing local.
Try it
Run scripts/setup_local_models.sh, scripts/setup_backend.sh, then bun install and scripts/dev.sh; open http://localhost:3000.
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 projectnot found in the excerpt0.19
- Shows a System One patternnot found in the excerpt0.25
- Describes handling uncertaintynot found in the excerpt0.08
- Reports measured numbersnot found in the excerpt0.10
- Is a runnable toolFound in material0.87
- Top-10 learning shortlist signalunclear0.43
- Is a replica of the modelnot found in the excerpt0.39
- Solves a common problem (0–2)score on a 0–2 scale1.28 / 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 4 Oct 2026.