Pinned Loading

1. agent-eval-toolkit agent-eval-toolkit Public

   Decision-oriented evaluation toolkit for LLM & agent systems, focusing on trust, failure modes, and deployment readiness in enterprise environments.

   Python

2. spk_balance spk_balance Public

   Evaluation-oriented MVP exploring speaking–writing feedback loops for agent and LLM communication quality.

   Python

3. agent-accountability-eval agent-accountability-eval Public

   An evidence-based system for evaluating agentic AI trustworthiness through accountability, continuous evaluation, and human-in-the-loop governance.

4. worldsim-eval worldsim-eval Public

   Evaluate AI agents by simulating world-level consequences.