Skip to content

Jev directory

Custos

Rust single-binary behavioral intrusion prevention system and cross-platform firewall bouncer (pf, nftables, ipset, netsh) that batches suspicious actors into Jev /v1/systemone calls and syncs threat intelligence across a fleet over gRPC.
Stars
0
Reading time
2 min
Published by
Community
Added
Nov 2026

Highlights

  • Three-tier pipeline: deterministic L1 filtering, prompt-injection sanitization, then batched Jev reasoning.
  • Packs up to 25 suspicious actors into one /v1/systemone request; about $0.00009 per 4-actor batch.
  • Bouncer writes to pf, nftables, ipset, and netsh; fleet nodes sync over gRPC HTTP/2.
  • Redacts credential parameters and Bearer/Basic values before samples are stored or sent to Jev.
  • Does not inspect bodies, cookies, raw protocol headers, or application authorization context.

Questions about this entry

Short answers drawn from the linked project or page.

Reactions & coverage

Posts, threads, and videos about this entry from around the web.

YouTube: Kubernetes admission control with a decision model, fail-closed.

Hacker News: SafeDep Gryph plus Jev checks for compromised coding-agent behavior.

2 pointsDetecting Compromised AI Coding Agents with Jev and GryphRead the thread on Hacker News

X: Jev and Laya on security queries

X: Testing Jev for prompt injection

From the Jev guides

Original write-ups on what this entry is for.

From the Jev AI model community

Posts from builders shipping with Jev right now.

Follow @typesafeai