Skip to content
@stanford-oval

Stanford Open Virtual Assistant Lab

Research projects in the Stanford Open Virtual Assistant Lab

Pinned Loading

  1. storm storm Public

    An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.

    Python 31.3k 2.9k

  2. WikiChat WikiChat Public

    WikiChat is an improved RAG. It stops the hallucination of large language models by retrieving data from a corpus.

    Python 1.6k 147

  3. suql suql Public

    SUQL: Conversational Search over Structured and Unstructured Data with LLMs

    Python 308 39

  4. genie-worksheets genie-worksheets Public

    Specification for creating reliable LLM-based conversational agents

    HTML 69 29

  5. spinach spinach Public

    SPINACH: SPARQL-Based Information Navigation for Challenging Real-World Questions

    Jupyter Notebook 77 26

  6. sliders sliders Public

    Repository for paper: Contexts are Never Long Enough: Structured Reasoning for Scalable Question Answering over Long Document Sets

    Python 29 3

Repositories

Showing 10 of 118 repositories
  • clinical-trial-matching Public

    Stanford OVAL Clinical Trial Matcher, developed with Mayo Clinic, combines SatIR and VERDICT for scalable, high-recall trial retrieval and accountable eligibility decisions using LLMs, databases, SMT, and MaxSAT. SatIR paper: https://arxiv.org/abs/2604.08849. VERDICT paper: https://arxiv.org/abs/2609.03366

    stanford-oval/clinical-trial-matching's past year of commit activity
    Python 4 Apache-2.0 0 0 0 Updated Sep 13, 2026
  • oval-website Public

    The new OVAL website

    stanford-oval/oval-website's past year of commit activity
    Astro 8 4 0 0 Updated Sep 4, 2026
  • DataSTORM Public

    DataSTORM: Deep Research on Large-Scale Databases using Exploratory Data Analysis and Data Storytelling https://arxiv.org/abs/2604.06474

    stanford-oval/DataSTORM's past year of commit activity
    Python 7 Apache-2.0 1 0 0 Updated Aug 19, 2026
  • suql Public

    SUQL: Conversational Search over Structured and Unstructured Data with LLMs

    stanford-oval/suql's past year of commit activity
    Python 308 Apache-2.0 39 5 2 Updated Aug 11, 2026
  • pyalmond Public

    Python client for the Almond API

    stanford-oval/pyalmond's past year of commit activity
    Python 5 BSD-3-Clause 3 0 2 Updated Jul 21, 2026
  • sliders Public

    Repository for paper: Contexts are Never Long Enough: Structured Reasoning for Scalable Question Answering over Long Document Sets

    stanford-oval/sliders's past year of commit activity
    Python 29 MIT 3 1 0 Updated Apr 26, 2026
  • Churro Public

    CHURRO is an OCR toolkit for historical document transcription, built to make handwritten and printed sources readable at high accuracy and lower cost.

    stanford-oval/Churro's past year of commit activity
    Python 74 Apache-2.0 5 4 1 Updated Apr 18, 2026
  • spinach Public

    SPINACH: SPARQL-Based Information Navigation for Challenging Real-World Questions

    stanford-oval/spinach's past year of commit activity
    Jupyter Notebook 77 Apache-2.0 26 4 0 Updated Feb 26, 2026
  • WikiChat Public

    WikiChat is an improved RAG. It stops the hallucination of large language models by retrieving data from a corpus.

    stanford-oval/WikiChat's past year of commit activity
    Python 1,616 Apache-2.0 147 8 2 Updated Jan 31, 2026
  • Lemonade Public

    LEMONADE: A Large Multilingual Expert-Annotated Abstractive Event Dataset for the Real World

    stanford-oval/Lemonade's past year of commit activity
    Python 22 Apache-2.0 4 1 0 Updated Nov 8, 2025
View all repositories