Repo · Data & extraction
jev-cvss
Fast CVSS scoring from vulnerability descriptions using Typesafe Jev.
Open github.com ↗From the repository
Fast CVSS scoring from vulnerability descriptions using Typesafe Jev
cvssjevtypesafe-ai
How builders describe it
Three Python scripts that have Jev pick CVSS metric values from a vulnerability description while the numeric scores are computed in code, following the FIRST v3.0, v3.1 and v4.0 specifications.
I made some CVSS classification scripts that use Jev to generate a CVSS vector for a given software vulnerability description. Currently supports CVSS 3.0, 3.1, and 4.0. Tested against several CVEs from NVD that have official CVSS scores and it's usually either exact or very close to the official…
The decision Jev makes
Keep or drop a row, assign a label, or select one field value at a time.
Where it fits
Putting Jev next to the data: filtering rows with plain-English conditions, classifying records, labelling datasets and pulling structure out of text one small decision at a time. All 98 data & extraction projects →
Related projects
Data & extractionomp-jevifyOh My Pi skill plugin: rubric-first bulk classification with judge_batch (Jev).GitHub · ★ 2 · ericjuta
Data & extractionclickhouse-jevNatural-language predicates, probabilities and classification for ClickHouse via executable UDFs backed by TypeSafe Jev; inspired by pg-jev with a…GitHub · ahwlsqja
Data & extractionfast-resume-scoringScore how well a resume fits a job in under a second with TypeSafe Jev and see which requirements it covers (reported one request, ~0.4 s).GitHub · dphbfs
Data & extractionIntelligentDocumentProcessing (Jev + Haiku)Hybrid invoice/document processing: TypeSafe Jev makes typed decisions (document type, supplier, completeness), Claude Haiku extracts, n8n…GitHub · DanielHuetteData & extractionHands-On-AI-EngineeringAn open-source data analyst agent that keeps Qwen for generating SQL and uses Jev as a review layer at three checkpoints: question clarity, SQL…GitHub · Sumanth
Data & extractionWorldMonitorReal-time geopolitical intelligence dashboard that uses TypeSafe Jev questions to score news headline severity into five threat levels and categorize…GitHub · ★ 88k