Automated README summary
Automatically summarized from the README on 21 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
An Android accessibility overlay for WeChat, QQ, and X chats. It reads visible messages, judges the other party's intent and risk, drafts three replies, and fills a chosen one into the input box without sending. For personal study and research.
How it uses Jev
Jev answers one batch of typed questions (about seven) on the captured recent messages: the other party's true intent, danger level (1-9), what they want, whether to reply now, and the best action, returning in about one second with confidence. Jev also ranks the three drafted replies by suitability with proportions.
Primitives:choicescorenoul
Technique worth stealing
One core plus a per-app ChatAppAdapter that turns the accessibility tree into title and messages; everything downstream is reused.
Try it
adb install -r apk/jev-assistant-v1.2-release.apk, then set an OpenRouter API key and enable permissions.
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 material0.91
- Shows a System One patternFound in material0.77
- Describes handling uncertaintynot found in the excerpt0.06
- Reports measured numbersFound in material0.79
- Is a runnable toolFound in material0.97
- Top-10 learning shortlist signalunclear0.57
- Is a replica of the modelnot found in the excerpt0.04
- Solves a common problem (0–2)score on a 0–2 scale0.98 / 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 21 Sept 2026.