Automated README summary
Automatically summarized from the README on 26 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A macOS floating panel for supported chat apps that reads on-screen messages (screenshot + Apple Vision OCR, or system text API), then shows the message's intent, a 0–9 risk level with suggested action, and reply candidates. Read-only, no injection or hooks.
How it uses Jev
Jev judges each incoming message: an 8-class intent distribution and a 0–9 risk score with action advice, from the message text plus chat context (history, quotes, background). The panel displays intent, recognition rate, risk level and advice; candidates are generated separately and re-ranked by a local model.
Primitives:choicescore
Technique worth stealing
Zero-shot intent classification and graded risk scoring from one local forward pass, used to drive a read-only overlay.
Try it
brew tap jev-chat/tap && brew install --cask jev-chat/tap/jev-jarvis, or run ./start.command from source.
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 projectunclear0.51
- Shows a System One patternnot found in the excerpt0.32
- Describes handling uncertaintynot found in the excerpt0.05
- Reports measured numbersFound in material0.94
- Is a runnable toolFound in material0.96
- Top-10 learning shortlist signalnot found in the excerpt0.32
- Is a replica of the modelFound in material0.61
- Solves a common problem (0–2)score on a 0–2 scale1.01 / 2
- About JevFound in material0.66
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 26 Oct 2026.