全部项目

相关项目

  • jev-shield

    Semantic MCP firewall powered by Jev — screens every tool call, tool result, and tool description with calibrated System One verification. 94% block recall, 0 false positives, ~$0.00002/check.

    共同主题: ai-safety

  • 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

  • adk-go-typesafe

    TypeSafe AI System One integration and utilities for adk-go

    共同主题: ai-tools