Automated README summary
Automatically summarized from the README on 19 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A reference design for real-time agents that moves small per-turn decisions off the critical path using a fast System One classifier, with a simulated support pack and browser demo.
How it uses Jev
Jev (or a compatible System One classifier) answers typed questions on partial and final transcripts: routing, protective flags, and output-guard checks. Results are calibrated probabilities used to choose scripts, small/large LLMs, speculative generation, or fail-closed holds.
Primitives:choicescorenoul
Technique worth stealing
Classify partial transcripts alongside the conversation; classifier outputs can only add caution, never unlock less-cautious paths.
Try it
python -m jevelin compare; python -m jevelin trace --call 0; python -m jevelin live --call 0
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 material0.87
- Shows a System One patternFound in material0.90
- Describes handling uncertaintynot found in the excerpt0.11
- Reports measured numbersnot found in the excerpt0.14
- Is a runnable toolFound in material0.78
- Top-10 learning shortlist signalunclear0.43
- Is a replica of the modelFound in material0.72
- Solves a common problem (0–2)score on a 0–2 scale1.68 / 2
- About JevFound in material0.84
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 19 Oct 2026.