Pinned Loading

1. apex-evals apex-evals Public

   Diagnostic eval framework for agentic tool execution failures across selection, argument construction, output use, and multi-tool chains.

   Python

2. safeshipper safeshipper Public

   AI safety measurement at scale

   Jupyter Notebook

3. data-bedrock data-bedrock Public

   The data foundation playbook for a startup's first Data Scientist.

   Jupyter Notebook

4. Vision-Mask-and-Attend Vision-Mask-and-Attend Public

   Visualize how human attend on images when detecting objects

   Python 3

5. ghost-watcher ghost-watcher Public

   Measuring and detecting multi-account subscription abuse in AI products.

   Jupyter Notebook

6. Char-NMT Char-NMT Public

   Forked from ceroper/ge

   Character Level Neural Machine Translation - German to English

   Python 9 6