Automated README summary
Automatically summarized from the README on 3 Nov 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A local web tool that analyzes two-person chat logs (WeChat, QQ, WhatsApp, iMessage) to show sentiment, intent, reply grades, and next-step suggestions for people wanting to understand a crush or partner better.
How it uses Jev
Jev is the preferred model for per-message analysis. The tool sends chat state and typed questions to Jev, which returns classification, scoring, and probabilities for sentiment and intent; these probabilities appear under chat bubbles and feed the overall affinity score and reply grade.
Primitives:choicescorenoul
Technique worth stealing
Use a native judgment model that returns calibrated probabilities for per-message sentiment and intent instead of free-text LLM output.
Try it
Run npm ci, npm run build, npm start, then open http://127.0.0.1:3178/ and configure the model key.
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-1.14.0- Project signals
jev-1.14.0- Category
jev-1.14.0- Pattern tags
jev-1.14.0
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 projectnot found in the excerpt0.06
- Shows a System One patternunclear0.41
- Describes handling uncertaintynot found in the excerpt0.25
- Reports measured numbersnot found in the excerpt0.02
- Is a runnable toolFound in material0.98
- Top-10 learning shortlist signalnot found in the excerpt0.11
- Is a replica of the modelnot found in the excerpt0.03
- Solves a common problem (0–2)score on a 0–2 scale0.62 / 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 3 Nov 2026.