Pinned Loading

1. rag-eval-observe rag-eval-observe Public

   RAG Eval Observability is a production-ready, open-source platform for building, evaluating, and monitoring Retrieval-Augmented Generation (RAG) systems. It pairs a ChatGPT-style UI with a robust b…

   Python

2. model-failure-lab model-failure-lab Public

   Toolkit for discovering, classifying, and debugging failure modes in LLM and RAG systems.

   Python 1

3. agentic-data-science-system agentic-data-science-system Public

   End-to-end agentic data science system combining deterministic financial analytics, MCP tool execution, and LLM-driven planning with full traceability, evaluation, and production-ready infrastructure.

   Python

4. LLMfromScratch LLMfromScratch Public

   LLMfromScratch is a hands-on, educational deep learning project that demystifies large language models by guiding practitioners through the end-to-end process of building and training a Transformer…

   Jupyter Notebook 1

5. Agentic-GenAI-Capstone-Google-Kaggle Agentic-GenAI-Capstone-Google-Kaggle Public

   Agent QA Mentor: an agentic QA pipeline that evaluates tool-using AI agent trajectories (scores, issue codes, safety/hallucination detection), rewrites prompts with targeted fixes, and stores long-…

   Jupyter Notebook

6. Research-AI-Agent Research-AI-Agent Public

   Tool-calling Research Assistant built with LangChain + Anthropic Claude that uses web search and Wikipedia to answer queries, returns a structured Pydantic-validated response, and can save results …

   Python