Pinned Loading

1. llm-inspect llm-inspect Public

   Inspect layer-level components of open weight LLMs during inference. E.g., extract activations at a target layer in response to prompts expected to elicit a particular state.

   Python

2. awesome-agent-sandboxes awesome-agent-sandboxes Public

   A comprehensive guide to sandboxing options for AI agents.

   Python 2

3. ai-control ai-control Public

   scaffolding for basic AI Control research experiments

   Python

4. alexandria alexandria Public

   Minimalist infrastructure for private collections, digital and/or physical.

   Python

5. otelex otelex Public

   OpenTelemetry Collector distribution with a custom exporter for extracting span attributes into a row-like map for export to a structured database.

   Go

6. micrograd-python micrograd-python Public

   An implementation of Karpathy's micrograd, as a basis for exploring the design decisions motivating the MLP architecture and gradient descent learning algorithm.

   Python