supervisor-guards is an open-source CLI tool that wraps unsafe agent actions with guardrails, providing runtime supervision and policy enforcement. It is designed for AI agent developers who need to ensure safe and controlled agent behavior.
supervisor-guards sits in PulseGate's Autonomous agents & workflows category. It focuses on adding guardrails and runtime supervision to unsafe agent actions in AI systems. It is built as an open-source project for AI agent developers and researchers. The project is open source (Apache-2.0). It runs on the command line.
It is developed by ArielSanroj, and it first shipped in 2026. The project is developed in the open on GitHub with 160 commits in the last 90 days. Key capabilities include agent guardrails, shadow mode, and policy engine.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do