Custodian-hermes-guard is an open-source Python package providing a fail-closed policy guard specifically for the Hermes Agent. It is managed by Talaria and ensures that policy violations result in safe failure states. Aimed at developers and teams deploying AI agents, it adds a layer of security and compliance to agent operations.
custodian-hermes-guard sits in PulseGate's LLM eval & observability category. It focuses on enforcing strict fail-closed policies for the Hermes AI agent to ensure secure and compliant operation. custodian-hermes-guard is an open-source project aimed at developers. The project is open source (MIT). custodian-hermes-guard is available on the command line, and it can be self-hosted.
Behind custodian-hermes-guard is KeyArgo, and it first shipped in 2026. The project is developed in the open on GitHub with 1 commit in the last 90 days.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Same category — not a similarity match