In the Security & compliance platforms space, Agentguard takes a focused approach. It focuses on controlling AI-agent access, tool use, and behavior through runtime policies and audits. Agentguard is a B2B product aimed at AI developers and platform engineers. It runs on the web, the command line, and API, and it can be self-hosted.
Whitzard builds and maintains Agentguard, and it first shipped in 2026. The project is developed in the open on GitHub with 124 stars and 132 commits in the last 90 days. Among its 8 catalogued features are runtime access control, Policy DSL, and jailbreak checks.
What PulseGate has recorded for this listing
Closest matches by what these projects do