jevegis
0xArx/jevegis
Guardrails for LLM apps in one API call. Prompt injection, jailbreaks, leaks, unsafe content. Built on TypeSafe Jev. MIT.
- スター
- 3
- フォーク
- 0
掲載理由
JevegisはTypeSafe Jevを使う検索・コンテンツ評価とTrust & Safetyモデレーションを説明し、閾値はアプリ側で適用します。
0xArx/jevegis
Guardrails for LLM apps in one API call. Prompt injection, jailbreaks, leaks, unsafe content. Built on TypeSafe Jev. MIT.
JevegisはTypeSafe Jevを使う検索・コンテンツ評価とTrust & Safetyモデレーションを説明し、閾値はアプリ側で適用します。
Sub-100ms security gate for AI agent tool calls, powered by TypeSafe's Jev (System-1) decision model. Single-request Choice/Noul/Score evaluation, dual-factor blocking matrix, calibrated-confidence routing, fail-closed parsing, zero-config local fallback. LangChain-ready.
共通トピック: guardrails, llm-security
Node.js bindings for TypeSafe's Jev — the System One model. Typed decisions, probabilities and confidence, with no text generation and no parsing.
共通トピック: guardrails
Vets an LLM agent's tool calls through TypeSafe AI's Jev before they run — allow, block, or hold, failing safe on uncertainty.
共通トピック: guardrails