Automated README summary
Automatically summarized from the README on 16 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
Jev-Mem is an agentic memory system for long-running AI agents. It organizes observations into semantic, temporal, causal, and entity graph views, then retrieves evidence for a System-Two language model to synthesize answers.
How it uses Jev
Jev makes memory decisions: memory typing, relation judgments, query routing, budget allocation, candidate scoring, and evidence assessment. It uses Noul (binary propositions) and Choice (categorical decisions) on memory state. Code validates outputs and enforces graph and retrieval limits.
Primitives:choicenoul
Technique worth stealing
Separate frequent memory-management decisions (System One) from deeper answer reasoning (System Two).
Try it
python -m jev_mem.demo
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 excerpt0.32
- Shows a System One patternnot found in the excerpt0.34
- Describes handling uncertaintynot found in the excerpt0.07
- Reports measured numbersnot found in the excerpt0.09
- Is a runnable toolnot found in the excerpt0.28
- Top-10 learning shortlist signalnot found in the excerpt0.23
- Is a replica of the modelFound in material0.67
- Solves a common problem (0–2)score on a 0–2 scale1.63 / 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 16 Oct 2026.