Jeff Guard Multilang

Patronus Studio's 151M-parameter Jev-like decision model for AI-agent security: given a serialized agent scene, a security question and answer options it returns calibrated probabilities in one pass, reporting 92.8 balanced accuracy on 10,576 held-out decisions.

Superagent's security triage model: a continual fine-tune of AutoJev-27B that returns calibrated probabilities for prompt-injection and content checks, with a release policy at 0.70 unsafe.

A local, non-autoregressive security guardrail suite powered by Convai Innovations' Laya model, returning typed decision probabilities for security inspection. It positions itself against Jev on latency and against generative LLMs on hallucination risk.

A fast, single-pass 2B System 1 model for robots' physical judgment: it reads a short text of what a robot senses and returns probabilities for the questions that matter in the moment, scoring 0.81 on its own benchmark against TypeSafe Jev's 0.28.

A safety guardrail for coding agents (Claude Code, Codex, Cursor, Antigravity, Grok) that intercepts shell commands, script executions and file writes before they run. Its neural tier can use Liquid AI d1-3B, CLM, TypeSafe Jev cloud or pure rules; a deterministic tier blocks destructive patterns in under 0.1 ms.

A proof-of-concept Python scanner that maps a backend codebase's attack surface and ranks likely vulnerabilities down to the suspicious line, using Jev as the classifier for about one cent per repo. It reads Python, JavaScript and TypeScript, and a demo site shows read-only results on PyGoat and NodeGoat.