Automated README summary
Automatically summarized from the README on 26 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
Jevlet is a research reconstruction of a Jev-like System-One model plus a daily-driver Windows assistant. It takes a state and typed questions, returns calibrated probabilities over runtime options, and never generates text.
How it uses Jev
Jevlet uses Jev-style Choice, Noul, and Score questions to decide routes, risk, urgency, and assistant actions. The state is the task and active window; options are installed apps, open windows, UI Automation controls, or spans of the user's words. Results drive the command palette and safety gate.
Primitives:choicescorenoul
Technique worth stealing
One packed sequence with isolated question branches and order-invariant option comparison via [DECIDE] query-key dot products.
Try it
python -m pip install -e ".[dev,semantic,desktop,colab]" then pythonw -m jevlet.app
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 material0.95
- Shows a System One patternFound in material0.85
- Describes handling uncertaintynot found in the excerpt0.06
- Reports measured numbersnot found in the excerpt0.06
- Is a runnable toolFound in material0.71
- Top-10 learning shortlist signalnot found in the excerpt0.30
- Is a replica of the modelFound in material0.95
- Solves a common problem (0–2)score on a 0–2 scale0.65 / 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 26 Sept 2026.