全部项目

jevshield

lgy1027/jevshield

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.

Python
星标
5
派生
0

收录依据

使用 Jev/System One 进行意图路由及工具调用决策,同时由应用保留编排、重试和最终回复职责的框架中立控制层。

相关项目

  • turnstile

    Guardrails for AI agent actions. Deterministic policy, Jev semantic checks, and replayable decisions.

    共同主题: agent-security, ai-agents, guardrails

  • jevegis

    Guardrails for LLM apps in one API call. Prompt injection, jailbreaks, leaks, unsafe content. Built on TypeSafe Jev. MIT.

    共同主题: guardrails, llm-security

  • jev-guard

    Vets an LLM agent's tool calls through TypeSafe AI's Jev before they run — allow, block, or hold, failing safe on uncertainty.

    共同主题: ai-safety, guardrails