Automated README summary
Automatically summarized from the README on 11 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A local tool that logs into Telegram as you (MTProto user client) and judges incoming messages and your drafts in real time, for people who want to know how a reply will land before sending it.
How it uses Jev
Jev returns structured judgments, not text. It scores each incoming message for emotion/intent/tone/events, preheats session-level affinity and relationship stage while the other person types, grades your sent messages, and scores drafts before sending (quality, emotional fit, 5 hit checks, timing).
Primitives:choicescorenoul
Technique worth stealing
Since Jev can't generate text, invert the design: you write the draft, Jev judges it before sending.
Try it
npm install; cp .env.example .env; fill keys; npm run login; npm start
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 material0.96
- Shows a System One patternFound in material0.65
- Describes handling uncertaintynot found in the excerpt0.05
- Reports measured numbersFound in material0.78
- Is a runnable toolFound in material0.82
- Top-10 learning shortlist signalFound in material0.72
- Is a replica of the modelnot found in the excerpt0.04
- Solves a common problem (0–2)score on a 0–2 scale0.96 / 2
- About JevFound in material0.98
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 11 Oct 2026.