Pinned Loading

1. Agent-Memory-Playground Agent-Memory-Playground Public

   A playground for agent memory designed for comparing how AI agents remember and forget. Run two agents side by side, each using a different memory strategy: sequential, sliding window, summarizati…

   Python

2. llm-mysql-eval llm-mysql-eval Public

   Systematically evaluate text-to-SQL systems for MySQL with automated validation and LLM-based semantic scoring.

   Jupyter Notebook

3. blamechain blamechain Public

   Blamechain is a CLI tool that turns messy Git history into clear narrative. It summarizes commits, extracts TODOs, tracks ownership drift, and maps file evolution - so devs can understand not just …

   JavaScript

4. RAG-hmo RAG-hmo Public

   A healthcare RAG app that builds an HMO profile, retrieves relevant medical documents, and generates personalized, bilingual answers to user questions

   Python

5. LucyDetect LucyDetect Public

   LucyDetect is an LLM Drift Analyzer designed to help researchers track AI model responses over time and detect inconsistencies, including hallucinations. It stores past responses, calculates drift …

   Python

6. Stealthee-MCP-tools Stealthee-MCP-tools Public

   Python