Agentack is an MIT-licensed Python package for testing human approval controls in AI agents. It helps developers evaluate agentic security workflows and verify that approval gates operate as intended.
In the Frameworks & runtimes space, agentack takes a focused approach. It focuses on testing whether human approval controls for AI agents reliably prevent unauthorized actions. It is built as an open-source project for AI agent developers and security engineers. agentack is open source under the MIT license. agentack is available on the command line, and it can be self-hosted.
It is developed by Sylvester Kaczmarek, and it first shipped in 2026. Development happens publicly on GitHub with 11 commits in the last 90 days. Key capabilities include approval controls, human-in-the-loop testing, and agent security testing.
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