Automated README summary
Automatically summarized from the README on 11 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A retrieval loop for a Markdown vault where a system-one model (Jev) makes the yes/no decisions instead of an LLM. Benchmarked against simple RAG and a Haiku-judged loop on 60 held-out questions.
How it uses Jev
Each turn, Jev scores candidate notes with options answer, step, none, returning a probability per option. A deterministic policy (src/loop/policy.ts) uses these scores to follow links, answer, rewrite the query or abstain. A Haiku fallback can run while no answer is kept.
Primitives:choice
Technique worth stealing
Replace LLM yes/no decisions in a retrieval loop with a system-one model returning probabilities per option.
Try it
bun install; bun src/cli.ts index corpus/dev/vault; bun src/cli.ts eval --config C --split test --fallback none
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 material0.81
- Shows a System One patternFound in material0.81
- Describes handling uncertaintynot found in the excerpt0.07
- Reports measured numbersFound in material0.86
- Is a runnable toolnot found in the excerpt0.21
- Top-10 learning shortlist signalunclear0.54
- Is a replica of the modelnot found in the excerpt0.12
- Solves a common problem (0–2)score on a 0–2 scale1.49 / 2
- About JevFound in material0.96
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 11 Oct 2026.