Guardrails service for AI agents. Default-deny tool call evaluation with LLM safety analysis, priority-ordered decision matrix, and human-in-the-loop escalations. Session recording, behavioral analysis, MCP proxy, secret redaction, and real-time audit.
Latest release v0.14.1 — Intaris 0.14.1 · 23 Oct 2026
1 file for Codex and OpenCode: intaris AGENTS.md — 22,724 tokens loaded in every session.
AGENTS.md D 22,724 tok These files are fpytloun/intaris's own configuration — they tell Codex and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.