turnstile
zyphr-labs/turnstile
Guardrails for AI agent actions. Deterministic policy, Jev semantic checks, and replayable decisions.
- スター
- 0
- フォーク
- 0
掲載理由
任意の Jev 検査と決定的な権限規則で選択されたツール操作を許可・要確認・拒否にする実験的ガードで、端末のサンドボックスではない。
zyphr-labs/turnstile
Guardrails for AI agent actions. Deterministic policy, Jev semantic checks, and replayable decisions.
任意の Jev 検査と決定的な権限規則で選択されたツール操作を許可・要確認・拒否にする実験的ガードで、端末のサンドボックスではない。
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.
共通トピック: agent-security, ai-agents, guardrails
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.
共通トピック: ai-agents, claude-code, guardrails
MCP server for Jev (TypeSafe AI's System One model) — give any agent typed, calibrated decisions: classify, score, check, gate risky tool calls. Try free: jevtypesafeai.com
共通トピック: ai-agents, claude-code