Automated README summary
Automatically summarized from the README on 4 Nov 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
MorrowCache is an open-source local proxy for OpenAI-compatible chat APIs that reuses cached final answers for paraphrased prompts and AI agent retries, reducing repeated model calls for developers and agent builders.
How it uses Jev
Jev (or a local System One adjudicator) decides whether a new request shares intent with a cached one, given the prior conversation and latest user ask. On admit, the stored final assistant text is returned; on error it fails open and calls the model.
Primitives:choice
Technique worth stealing
Calibrated same-intent admits instead of cosine similarity, with freshness checks and fail-open behavior to keep false HITs low.
Try it
npx @kushalicious/jevcache@latest start (Node ≥ 22.5); set ADJUDICATOR=kev|laya for local.
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-1.14.0- Project signals
jev-1.14.0- Category
jev-1.14.0- Pattern tags
jev-1.14.0
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 excerpt0.15
- Shows a System One patternnot found in the excerpt0.15
- Describes handling uncertaintynot found in the excerpt0.04
- Reports measured numbersnot found in the excerpt0.02
- Is a runnable toolFound in material0.99
- Top-10 learning shortlist signalnot found in the excerpt0.07
- Is a replica of the modelnot found in the excerpt0.09
- Solves a common problem (0–2)score on a 0–2 scale1.55 / 2
- About JevFound in material0.97
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 Nov 2026.