Pinned Loading

1. OpenGrad OpenGrad Public

   Open research infrastructure for measuring capability-efficiency tradeoffs in post-trained small open-weight language models.

   Python

2. OpenPapers OpenPapers Public

   Provenance-first MCP server for reproducible LLM and ML research

   TypeScript

3. SchemaForge SchemaForge Public

   Hybrid deterministic + distilled LLM structured extraction (JSON): schema registry, hard-example generation, teacher-validation gate, knowledge distillation, hybrid routing. V2/V3 research whitepap…

   Python

4. small-mind-companion small-mind-companion Public

   2B-GF: stretching a 1B parameter LLM through post-training and external cognitive architecture (implementation repo)

   Python