agentbench-cli is an open-source command-line tool that allows AI developers and researchers to evaluate, test, and scan the behavior and safety of AI agents. It provides automated checks and reporting for agent performance and compliance.
In the LLM eval & observability space, agentbench-cli takes a focused approach. It focuses on testing and evaluating the behavior and safety of AI agents via command line. It is built as an open-source project for AI developers and researchers. agentbench-cli is open source under the MIT license. It runs on the command line.
EdList builds and maintains agentbench-cli, and it first shipped in 2026. The project is developed in the open on GitHub with 25 commits in the last 90 days. Among its 4 catalogued features are agent evaluation, behavioral testing, and safety scanner.
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