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
A Hermes Agent plugin for Scelestine that records lessons from tool failures and user corrections, recalls relevant ones during turns, and promotes recurring lessons into standing behaviors in SOUL.md. Storage is Mnemosyne-only.
How it uses Jev
Jev makes three decisions: a choice question ranks shortlisted lessons for recall (top 3 injected); a noul question gates whether a tool failure or user correction is a reusable lesson; a Jev call estimates importance in adept_remember. Results are probabilities used as scores or thresholds.
Primitives:choicenoul
Technique worth stealing
Use one Jev choice question with all candidates as named options instead of N binary questions; rank by lift (score × roster size) rather than raw probability.
Try it
git clone, copy to ~/.hermes/plugins/, hermes plugins enable scelestine-adept, hermes gateway restart.
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 patternunclear0.54
- Describes handling uncertaintynot found in the excerpt0.05
- Reports measured numbersnot found in the excerpt0.04
- Is a runnable toolFound in material0.94
- Top-10 learning shortlist signalnot found in the excerpt0.27
- Is a replica of the modelnot found in the excerpt0.24
- Solves a common problem (0–2)score on a 0–2 scale1.02 / 2
- About JevFound in material0.95
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.