jevbooks

← All projects

jev-mail-triage

soderlind/jev-mail-triage

Local spam and phishing triage for Proton Mail Bridge, powered by TypeSafe Jev.

Automated README summary

Automatically summarized from the README on 14 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.

What it is

A Mac tool that reads new Proton Mail messages through Proton Mail Bridge and asks TypeSafe's Jev model whether each is unsolicited spam or a scam/phishing attempt. By default it only records answers; moves to a 'Jev Review' folder are opt-in and nothing is deleted.

How it uses Jev

For each message, Jev is asked two questions: is this unsolicited spam, and is this a scam or phishing attempt. The sender, subject, shortened text body, and link addresses are sent to TypeSafe. Scores are compared against configurable spam_threshold and scam_threshold; if a score is at or above its threshold and moves are enabled, the message is moved to a 'Jev Review' folder.

Primitives:score

Technique worth stealing

A local gate decides obvious cases on the Mac first, so fewer messages need to be sent to TypeSafe.

Try it

git clone the repo, install with pip, set secrets in Keychain, then run poll or serve.

View on GitHub

Start using Jev: API key and your first request →

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 material0.90
  • Shows a System One patternunclear0.47
  • Describes handling uncertaintynot found in the excerpt0.06
  • Reports measured numbersnot found in the excerpt0.07
  • Is a runnable toolFound in material0.93
  • Top-10 learning shortlist signalnot found in the excerpt0.32
  • Is a replica of the modelnot found in the excerpt0.04
  • Solves a common problem (0–2)score on a 0–2 scale1.03 / 2
  • About JevFound in material0.98
Signals
Jev is core to the project0.90Shows a System One pattern0.47Describes handling uncertainty0.06Reports measured numbers0.07Is a runnable tool0.93Top-10 learning shortlist signal0.32Is a replica of the model0.0400.51Solves a common problem (0–2)1.03 / 2012

no-judgment band (0.40–0.60)

Design patterns
Funnel0.97Traffic light0.79Questionnaire0.57Check-up0.41Viewfinder0.40Fail open, fail closed0.35Grey zone0.2300.51

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 14 Oct 2026.