jevprune

Filter command output for coding agents using a task description.

How it uses Jev

Jev is TypeSafe's decision model. Selection needs an early-access TypeSafe API key from the waitlist at typesafe.ai.

Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README.

Keep exploring

Similar to jevprune

Browse all
pi-jev-sentinel project preview
Agent tooling
Pi coding-agent extension: TypeSafe Jev checks for tool calls, tool outputs and replies (prompt injection, approvals, secret scrubbing, task pinning)
jev-cli (Nasrallah-AL) project preview
Command-line tool for TypeSafe's Jev AI model
jgrep project preview
Agent tooling
grep, but the pattern is a description. Filters lines by meaning with TypeSafe's Jev decision model: ~200 ms and a thousandth of a cent per line.
jev-codes project preview
Benchmarks & research
Audit your git diff against YAML coding-standards packs using TypeSafe's Jev model, from a CLI or your AI agent's command/skill.
jev-cvss project preview
Applications
Fast CVSS scoring from vulnerability descriptions using Typesafe Jev
jev-resume-match project preview
Demos & playgrounds
Score how well a resume matches a job description using Jev (TypeSafe AI). Next.js app that returns typed, explainable match scores instead of generated text.
ai-cli project preview
Integrations
Vercel Labs terminal CLI that can run Jev as the evaluation model for its evaluate command.
scam-shield project preview
Applications
Scam text message filter powered by TypeSafe's Jev model
jev-browser project preview
Browser & computer use
Browser use using Typesafe's Jev model