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 Windows desktop HUD that reads the open WeChat conversation via local offline OCR, groups messages by speaker, and tells you who needs you. It never sends messages or injects into WeChat.
How it uses Jev
Jev judges each speaker's role and intent from OCR-extracted messages plus local context (group type, relationship, nickname). A first coarse pass ranks all speakers; a second pass fully judges the top K. Choice and Noul answers feed code-side three-state gating (alert/todo/silent) and separate risk scores.
Primitives:choicescorenoul
Technique worth stealing
Judge people, not messages: aggregate by speaker so ambiguous replies gain context, and split risk into independent Noul labels.
Try it
pip install -r requirements.txt, copy .env.example to .env with your TypeSafe API Key, then python -m wechat_triage_hud.hud
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 material0.90
- Shows a System One patternFound in material0.75
- Describes handling uncertaintynot found in the excerpt0.08
- Reports measured numbersnot found in the excerpt0.05
- Is a runnable toolFound in material0.88
- Top-10 learning shortlist signalnot found in the excerpt0.29
- Is a replica of the modelnot found in the excerpt0.06
- Solves a common problem (0–2)score on a 0–2 scale1.10 / 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 19 Oct 2026.