# stanford-oval/storm

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

Repository: https://github.com/stanford-oval/storm
Canonical: https://ross.abutalabs.com/products/storm
Homepage: http://storm.genie.stanford.edu
Language: Python
License: MIT
License Family: permissive
Topics: large-language-models, nlp, knowledge-curation, naacl, report-generation, retrieval-augmented-generation, emnlp2024, agentic-rag, deep-research
Last push: 2025-09-30T18:07:21+00:00

## Health v2 (maintenance only)
Score: 38/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 44, release rhythm 16, longevity 63
- inputs: {"age_days": 892, "days_push": 337, "days_rel": 587, "gap_med": 119, "n_releases_24m": 2}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 31135, forks 2926 (observed 2026-08-28T04:11:56.579930+00:00)

## What it is
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
- artifact type: library
- maturity: active
- function: rag, llm-inference, agent-framework, search-engine, nlp, web-scraping
- domain: large-language-models, artificial-intelligence, documentation
- platform: python, cli
- tags: 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
- stanford-oval/storm (main) score 38

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:56.579930+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:52:19.347494+00:00, confidence not recorded.
  - readme: https://github.com/stanford-oval/storm (fetched 2026-08-28T04:11:56.579930+00:00, sha 8b10abafaeab)
  - homepage: http://storm.genie.stanford.edu (fetched 2026-08-29T07:49:25.894169+00:00, sha caa1c9f3a7de)
- Data as of 2026-08-30T08:39:29.467469+00:00.