hermia is an open-source command-line tool that provides an interactive TUI for evaluating large language model (LLM) agents. It supports both local and cloud-based models, enabling researchers and developers to test agentic behaviors, perform red-teaming, and assess security. Ideal for AI practitioners focused on model robustness and safety.
In the LLM eval & observability space, hermia takes a focused approach. It focuses on evaluating and testing LLM agent behavior and security across local and cloud models from the command line. It is built as an open-source project for AI researchers and developers. hermia is open source under the MIT license. hermia is available on the command line.
hermia first shipped in 2026. Key capabilities include agent evaluation, TUI interface, and local model support.
Latest indexed changes and source events
Other apps tracked under the same category.
