JevLang
TimMikeladze/JevLang
A policy engine for LLM decisions: declare routes, gates and actions once in TypeScript or Python, and every decision comes validated, explainable, replayable and audited.
- スター
- 1
- フォーク
- 0
掲載理由
掲載理由は準備中です
参照元を見るTimMikeladze/JevLang
A policy engine for LLM decisions: declare routes, gates and actions once in TypeScript or Python, and every decision comes validated, explainable, replayable and audited.
掲載理由は準備中です
参照元を見る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
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
共通トピック: agent, guardrails
Per-turn model & reasoning routing for Codex, driven by Jev (TypeSafe System One): picks the model, thinking depth and speed mode for every turn.
共通トピック: agent