jevguard
seb4ez/jevguard
Deterministic decision runtime, zero-token caching, and certainty calibrator for TypeSafe AI (Jev).
- 星标
- 0
- 派生
- 1
收录依据
Python 库在 Jev 外层提供确定性的状态裁剪、JSON 指纹、本地缓存和校准护栏,而不改变上游概率模型。
seb4ez/jevguard
Deterministic decision runtime, zero-token caching, and certainty calibrator for TypeSafe AI (Jev).
Python 库在 Jev 外层提供确定性的状态裁剪、JSON 指纹、本地缓存和校准护栏,而不改变上游概率模型。
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.
共同主题: ai-agents, guardrails
Typed judgment tools for MCP agents. TypeSafe's Jev model as verify, screen, find, classify, rerank, decide, compare, extract, review, gate, and score: the model judges, policy decides auto, review, or escalate.
共同主题: ai-agents, guardrails
Official Model Context Protocol (MCP) server for JevGuard and TypeSafe AI
共同主题: ai-agents, guardrails