jevbooks

← All projects

jev-runtime-security

ringzerosec/jev-runtime-security · Homepage

Kernel-enforced runtime security for AI agents, with optional Jev checks.

Verification & Guardrails0.91Runner-up: Scoring & RankingFunnel
Automated README summary

Automatically summarized from the README on 11 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.

What it is

Ring Zero Security enforces Linux BPF LSM policy for AI coding agents, deciding what each agent can read, run, install and connect to, and recording every refusal. It is for administrators and developers who need deterministic, kernel-level containment of agent actions.

How it uses Jev

Jev is an optional checks provider, off by default. When enabled, it scores tool calls or selected instruction-bearing files; a score can only raise a finding's severity, never permit what kernel policy denies. The README does not describe how Jev's output is consumed in code.

Primitives:score

Technique worth stealing

Enforce policy at the syscall via BPF LSM; use model scores only to raise severity, never to allow.

Try it

Install the .deb, run rz status, then bash examples/boundary-demo.sh to watch a kernel denial.

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 projectnot found in the excerpt0.05
  • Shows a System One patternnot found in the excerpt0.15
  • Describes handling uncertaintynot found in the excerpt0.08
  • Reports measured numbersnot found in the excerpt0.05
  • Is a runnable toolFound in material0.88
  • Top-10 learning shortlist signalnot found in the excerpt0.14
  • Is a replica of the modelnot found in the excerpt0.03
  • Solves a common problem (0–2)score on a 0–2 scale1.69 / 2
  • About JevFound in material0.77
Signals
Jev is core to the project0.05Shows a System One pattern0.15Describes handling uncertainty0.08Reports measured numbers0.05Is a runnable tool0.88Top-10 learning shortlist signal0.14Is a replica of the model0.0300.51Solves a common problem (0–2)1.69 / 2012

no-judgment band (0.40–0.60)

Design patterns
Funnel0.8800.51

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 11 Oct 2026.