17 results for tag "modal"
A large collection of Claude Code skill templates sponsored by Z.AI, providing ready-to-use development skill configurations across various domains.
**Seer** by ajobi-uhc β a library for interpretability researchers working with AI agents that launches sandboxed environments on Modal (GPU or CPU), lets agents operate via an IPython kernel with live visibility, and supports complex techniques like SAE-based checkpoint diffing and Petri-style auditing with whitebox tools.
Claude Code plugins for cloud deployment and full-stack development
Benchmark and evaluate interpretability agents for understanding and explaining machine learning model behaviors across different datasets and tasks.