Kratos-Analytics-LLC/AgentRails

A domain-agnostic safety layer for AI agents: declarative policy, dry-run, audit ledger and circuit breaker between an agent's proposed actions and their execution.

2 best points · 0 comments · 1 Hacker News post · 1 GitHub stars · View on GitHub

Hacker News discussions

• AgentRails – a safety layer for AI agents that take real actions (2 points, 0 comments, by KratosAnalytics, 2026-08-04)