Automated README summary
Automatically summarized from the README on 4 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
DGUI-HyperMem is a self-hosted long-term memory MCP server for AI agents, running on Cloudflare Workers. It stores durable memories, recalls them via hybrid vector and full-text search, and self-maintains by superseding near-duplicates.
How it uses Jev
JEV assigns each memory a type, salience score, and durability judgement, dropping non-durable chatter. It re-ranks fused retrieval candidates so the best memory wins despite wording differences, and runs contradiction checks that supersede memories. Decisions are logged to a HuggingFace dataset.
Primitives:choicenoulscore
Technique worth stealing
Log every JEV decision as an instruction row to build a training corpus for the reasoning layer.
Try it
npm install, create D1 and Vectorize resources, apply migrations, set secrets, then npx wrangler deploy.
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 projectFound in material0.73
- Shows a System One patternnot found in the excerpt0.25
- Describes handling uncertaintynot found in the excerpt0.05
- Reports measured numbersnot found in the excerpt0.05
- Is a runnable toolFound in material0.95
- Top-10 learning shortlist signalnot found in the excerpt0.34
- Is a replica of the modelunclear0.53
- Solves a common problem (0–2)score on a 0–2 scale1.20 / 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 Oct 2026.