Popular repositories Loading

1. finBERT finBERT Public

   Financial Sentiment Analysis with BERT

   Jupyter Notebook 2.2k 531

2. BESH BESH Public

   Python 26 2

3. Murphy Murphy Public

   Python 25 3

4. MemEval MemEval Public

   Benchmark suite for evaluating agent and LLM memory systems

   Python 25 4

5. stack-eval stack-eval Public

   Official implementation for the paper, StackEval: Benchmarking LLMs in Coding Assistance, https://arxiv.org/abs/2412.05288

   Python 20 4

6. prism prism Public

   Give Claude Code persistent memory — captures patterns from your sessions, validates them with AI, and surfaces team knowledge as reusable skills

   Python 19 1