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
Jev-Mem gives persistent AI agents a structured memory: it stores observations with provenance, links them across semantic, temporal, causal and entity graphs, and retrieves evidence for a System-Two language model to answer from.
How it uses Jev
Jev acts as the System-One controller. It judges inferred memory relations on candidate observations, routes queries across graph views, allocates traversal budgets, scores candidates, and assesses whether evidence is sufficient. Outputs are typed Noul and Choice decisions; ordinary code validates them and enforces graph and retrieval limits.
Primitives:choicenoul
Technique worth stealing
Split frequent memory-management decisions into a typed System-One controller, leaving answer synthesis to a System-Two model.
Try it
python -m jev_mem.demo (offline, no API keys); live runs need TYPESAFE_API_KEY and OPENAI_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 projectnot found in the excerpt0.31
- Shows a System One patternnot found in the excerpt0.33
- Describes handling uncertaintynot found in the excerpt0.07
- Reports measured numbersnot found in the excerpt0.08
- Is a runnable toolnot found in the excerpt0.32
- Top-10 learning shortlist signalnot found in the excerpt0.23
- Is a replica of the modelFound in material0.68
- Solves a common problem (0–2)score on a 0–2 scale1.62 / 2
- About JevFound in material0.90
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.