Pinned Loading

1. RivaLLMatch RivaLLMatch Public

   RivaLLMatch is an application that manages an arena in which different language models compete with each other. The basic concept is that models themselves evaluate each other.

   Python

2. TalentScoutAI TalentScoutAI Public

   TalentScoutAI is an application that uses a multi-agent framework to evaluate candidate profiles for job offers. This project aims to streamline the hiring process by providing detailed assessments…

   Python 1 1

3. dorsz dorsz Public

   Dokładne Odpytywanie Rozpoznające Sedno Zagadnienia. Projekt do testów Bielika z wykorzystaniem OpenAI Agents SDK.

   Python

4. LLMTest_NeedleInAHaystack LLMTest_NeedleInAHaystack Public

   Forked from gkamradt/LLMTest_NeedleInAHaystack

   Doing simple retrieval from LLM models at various context lengths to measure accuracy

   Jupyter Notebook

5. rag-lens rag-lens Public

   A clear lens for testing and benchmarking Retrieval-Augmented Generation (RAG) systems on Wikipedia, evaluated with the FRAMES benchmark.

   Python

6. ultimate-mcp ultimate-mcp Public

   The Ultimate MCP Server truly AGI‑ready out of the box.

   Python