Semantic firewall for LLM agents: tool calls gated by TypeSafe Jev (System One decision model via OpenRouter) + deterministic policy. PoC with corpus, stability eval, baseline, results.
The link points at the commit we read, so the line number still holds.
This one cannot run here
Its question set is assembled at runtime, or never written out literally in the code, so there is nothing to lift. The source link above will show you.
Other projects in this category
jev-review ▶ — A staged code-review workflow and local dashboard built with TypeSafe Jev.
oxlint-plugin-jev ▶ — Lint rules written in plain English. Oxlint finds the code, TypeSafe Jev answers the question.
patdown ▶ — typesafe's jev as a "fuzzy linter". give your code an ocular patdown.
jev_antispam_bot ▶ — Minimal grammY Telegram anti-spam bot powered by TypeSafe Jev
pi-heed ▶ — Runtime constraints for the pi coding agent: checks every side-effecting tool call against what you said, before it runs. Powered by TypeSafe Jev.
mastra-jev-moderation ▶ — Input moderation for Mastra agents on TypeSafe Jev — one file
gg-friggin-ez ▶ — Fast, drop-in profanity and toxicity screener for Node.js, powered by TypeSafe AI Jev. Catches leetspeak, character spacing, and romanized profanity across languages including Kannada, Telugu, Tamil, Hindi, and Bengali. ~50-500ms latency.
actiongate-jev ▶ — Runtime authorization and guardrails for AI-agent tool calls with deterministic policy and TypeSafe Jev via OpenRouter.