jevegis
0xArx/jevegis
Guardrails for LLM apps in one API call. Prompt injection, jailbreaks, leaks, unsafe content. Built on TypeSafe Jev. MIT.
- 星标
- 3
- 派生
- 0
收录依据
Jevegis 文档说明它使用 TypeSafe Jev 做检索/内容评估与信任安全审核,并由应用代码应用阈值。
0xArx/jevegis
Guardrails for LLM apps in one API call. Prompt injection, jailbreaks, leaks, unsafe content. Built on TypeSafe Jev. MIT.
Jevegis 文档说明它使用 TypeSafe Jev 做检索/内容评估与信任安全审核,并由应用代码应用阈值。
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: 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.
共同主题: guardrails
Vets an LLM agent's tool calls through TypeSafe AI's Jev before they run — allow, block, or hold, failing safe on uncertainty.
共同主题: guardrails