Automated README summary
Automatically summarized from the README on 29 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A Manifest V3 Chrome extension that lets users control the browser by voice. Chrome transcribes speech for free; Jev, TypeSafe's decision model via OpenRouter, decides what to do; plain code rules turn probabilities into page actions.
How it uses Jev
Jev answers typed questions per phrase: is_command, finished, multiple, intent (41 options), target (page elements), dangerous, site, tab, macro, media_action, and amount. lib/rules.js decide() converts these probabilities into actions; text, numbers and queries are pulled from the transcript by code.
Primitives:choicescorenoul
Technique worth stealing
One POST /api/alpha/decisions call per phrase with up to 11 parallel questions; long option lists go in a second small pick call only when needed.
Try it
Load unpacked in chrome://extensions, paste an OpenRouter key in the side panel, click Começar a ouvir.
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 material0.94
- Describes handling uncertaintynot found in the excerpt0.27
- Reports measured numbersnot found in the excerpt0.07
- Is a runnable toolFound in material0.98
- Top-10 learning shortlist signalunclear0.45
- Is a replica of the modelnot found in the excerpt0.03
- Solves a common problem (0–2)score on a 0–2 scale0.69 / 2
- About JevFound in material0.95
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 29 Sept 2026.