Automated README summary
Automatically summarized from the README on 14 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A Windows companion window for chat apps. It screenshots your own chat window, runs local offline OCR to read incoming messages, and suggests replies. For people who want help drafting responses without any automation of sending.
How it uses Jev
Jev judges the conversation: intent, tension, suggested action, and ranks three drafted replies by win probability. It runs on the recent N messages (default 10) plus relationship and style settings. Results appear as a summary and probability-labeled candidates in the floating window.
Primitives:choicescorenoul
Technique worth stealing
Three-stage pipeline: Jev judges intent first, that judgment is fed as a cheat-sheet to the drafting LLM, then Jev ranks the drafts.
Try it
Download the latest release zip, extract, run jev-chat-windows.exe, enter two API keys.
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 material0.88
- Shows a System One patternnot found in the excerpt0.27
- Describes handling uncertaintynot found in the excerpt0.04
- Reports measured numbersnot found in the excerpt0.04
- Is a runnable toolFound in material0.98
- Top-10 learning shortlist signalnot found in the excerpt0.32
- Is a replica of the modelnot found in the excerpt0.12
- Solves a common problem (0–2)score on a 0–2 scale0.98 / 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 14 Oct 2026.