Automated README summary
Automatically summarized from the README on 18 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
jevmem is a Claude Code plugin (also Cursor, Codex, Claude Desktop via MCP) that records decisions, rules, bugs, to-dos and dead ends from chats into a JEVMEM.md file in the repo, then brings relevant lines back in later sessions.
How it uses Jev
Jev answers yes/no questions with probabilities about whether a decision is worth keeping; if it is, jevmem writes one line to JEVMEM.md. Jev also picks the sentences that state the memory and its reason. A guard checks tool calls against saved rules before Claude runs them.
Primitives:choice
Technique worth stealing
Use a probability model as a filter: only persist a chat decision when Jev's yes/no probability says it is worth keeping.
Try it
npm install -g jevmem; cd your-project; jevmem setup (needs a TypeSafe API key).
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 projectunclear0.46
- Shows a System One patternnot found in the excerpt0.29
- Describes handling uncertaintynot found in the excerpt0.04
- Reports measured numbersnot found in the excerpt0.04
- Is a runnable toolFound in material0.96
- Top-10 learning shortlist signalnot found in the excerpt0.31
- Is a replica of the modelnot found in the excerpt0.04
- Solves a common problem (0–2)score on a 0–2 scale1.34 / 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 18 Oct 2026.