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
Sorts a Gmail inbox using a System One model to judge each email and plain Python to act on the judgement. Built to clear an 18,000-email inbox and keep it clear, with reversible actions and no permanent deletion.
How it uses Jev
Jev answers a fixed set of yes/no questions (keep questions like personal/important, cleanup questions like expired_code) on sender, subject, and preview snippet. The returned probabilities are thresholded in code (keep_at, cleanup_below) to decide keep, archive, or review; starred mail and always_clean senders bypass inference.
Primitives:choice
Technique worth stealing
Ask fixed yes/no questions about what an email is, not what to do with it; let code apply thresholds and dates.
Try it
Dry-run first: .venv/bin/python -m gmail_cleanup --limit 50; add --apply to act.
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 patternFound in material0.61
- Describes handling uncertaintynot found in the excerpt0.03
- Reports measured numbersFound in material0.97
- Is a runnable toolFound in material0.83
- Top-10 learning shortlist signalnot found in the excerpt0.21
- Is a replica of the modelnot found in the excerpt0.14
- Solves a common problem (0–2)score on a 0–2 scale1.08 / 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 3 Nov 2026.