Automated README summary
Automatically summarized from the README on 28 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
jevmem gives AI agents persistent long-term memory in one SQLite file, exposed as an MCP server, Claude Code/Cursor hooks, a CLI and a Python library, so decisions and gotchas survive across sessions without calling a generative LLM.
How it uses Jev
Jev answers typed questions with probabilities: on write, it types the note and screens it for injection, secrets and status rot, then links it to related notes; on recall it judges relevance, decides lite vs full mode and whether results are sufficient; every 20 writes it flags superseded, duplicate or repeated notes.
Primitives:choicescorenoul
Technique worth stealing
Split work: a cheap System One model answers typed probability questions for screening, typing, linking and sufficiency, while the agent does the writing and synthesis.
Try it
uvx jevmem config init --api-key "...", then claude mcp add --scope user jevmem -- uvx --from jevmem jevmem-mcp
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 projectFound in material0.86
- Shows a System One patternnot found in the excerpt0.28
- Describes handling uncertaintynot found in the excerpt0.04
- Reports measured numbersnot found in the excerpt0.04
- Is a runnable toolFound in material0.97
- Top-10 learning shortlist signalnot found in the excerpt0.30
- Is a replica of the modelnot found in the excerpt0.24
- Solves a common problem (0–2)score on a 0–2 scale1.50 / 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 28 Oct 2026.