PyModel/jev-judge-mcp

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.

语言：Python · GitHub 星标：49 · Fork：5

话题：agent-tools · ai-agents · ai-guardrails · classification · claude-code · fact-checking · guardrails · llm

在 GitHub 上查看原仓库