5 projects
openinterp-mcp
MCP server + Colab backend for mechanistic interpretability research. Bring-your-own-agent. Privacy-first.
openinterp
Python SDK + CLI for openinterp.org — Atlas search, SAE Traces, FabricationGuard hallucination detection, AgentProbeGuard mid-reasoning gate for code agents, InterpScore. The operational layer for mechanistic interpretability.
mechreward
Mechanistic interpretability as reward signal for RL training of LLMs
hlwq
Hadamard-Lloyd Weight Quantization for LLMs (placeholder reservation)
polarquant
PolarQuant: Hadamard-rotated Lloyd-Max quantization for LLM compression. Native HF transformers integration + weights + KV cache + CLI.
