Agent Control is an open-source control plane for governing AI agents at runtime. It centralizes policies for access control, safety guardrails, accuracy checks, audit logs, and tool-call enforcement across agent platforms.
In the Frameworks & runtimes space, Agent Control takes a focused approach. It focuses on governing and enforcing safety, security, and compliance policies across AI agents at runtime. It is built as an open-source project for AI platform engineers and developers operating agent fleets. Agent Control is open source under the Apache-2.0 license. It runs on the web, and it can be self-hosted.
It is developed by agentcontrol/agent-control, and it first shipped in 2025. The project is developed in the open on GitHub with 299 stars and 25 commits in the last 90 days. Among its 9 catalogued features are policy enforcement, access controls, and safety guardrails. It exposes integrations via a public API.
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