stanford-oval/storm

Health v2 · maintenance only

Adoption not part of the score

31135 stars · 2926 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

STORM is an LLM-powered system that researches a topic via internet search and generates full-length, cited, Wikipedia-like reports. It is distributed as the `knowledge-storm` Python package with a customizable pipeline for language models and retrieval backends.

Use cases

• generate a cited research report on any topic
• write wikipedia-style articles from scratch with llms
• deep research on a topic with citations
• collaborative knowledge curation with ai
• ground report generation on my own documents
• automate literature-style topic overviews

When to choose

• you need long-form, cited reports generated automatically from web research
• you want a customizable RAG pipeline supporting different LLMs and retrieval sources
• you want human-AI collaborative knowledge curation (Co-STORM)

When to avoid

• you need publication-ready articles without editing
• you need a simple single-prompt summarizer rather than a multi-stage research pipeline
• you lack API keys for LLMs and search engines

Facets

library · maturity active

rag llm-inference agent-framework search-engine nlp web-scraping large-language-models artificial-intelligence documentation python cli deep-research report-generation knowledge-curation wikipedia-style-articles citations co-storm litellm research retrieval-augmented-generation natural-language-processing ai-agents web-server

Member repositories

For agents

markdown · JSON · MCP: product_card(name="stanford-oval/storm")