すべてのプロジェクト

approval-judge-bridge

oppih/approval-judge-bridge

OpenAI-compatible judge endpoint for agent approval gates: typed judgements (Jev), any OpenAI-compatible model, or a rule file — fail-closed, calibrated, with a replay battery

Python
スター
0
フォーク
0

掲載理由

エージェントのコマンド承認を Jev の型付き判定から APPROVE/DENY/ESCALATE に変換し、判定不能時は人に委ねるブリッジ。

関連プロジェクト

  • open-jev-approvals

    Binary approval gate for Codex and Claude Code — every intercepted tool call is reviewed by TypeSafe JEV and composed through a versioned local policy, with scoped authorization.

    共通トピック: agent, guardrails

  • guardrails-md

    opencode plugin: a System One decision model judges every bash command before it runs — destructive / credentials / your guardrails.md policy

    共通トピック: ai-safety, guardrails

  • jev-watchdog

    Event-driven trajectory watchdog for coding agents: per-event LLM judgments (Jev, Claude, GPT) accumulated into quarantine decisions

    共通トピック: ai-safety, guardrails