# STORM

> Open-source AI that writes Wikipedia-style reports with citations

STORM is a research prototype from Stanford's Open Virtual Assistant Lab that researches a topic through Internet search and writes a Wikipedia-like report with citations. It works by collecting different perspectives on the topic and simulating a conversation between a writer and a topic expert. Co-STORM, a collaborative mode, lets the user join a discussion among AI experts while a mind map organizes what has been found. The code is open source, and a hosted research preview runs in the browser.

- **Category:** AI Research Tools
- **Made by:** Stanford Open Virtual Assistant Lab (OVAL)
- **Website:** https://storm.genie.stanford.edu
- **Runs on:** Web
- **Facts last checked:** Oct 5, 2026

## Pricing

STORM is free to use.

- **Pricing model:** Free
- **Free plan:** Free research preview with no paid plans. The code is open source under the MIT license; running it yourself needs your own language model and search API keys.
- **Free trial:** None listed.

| Plan | Price | What you get |
| --- | --- | --- |
| Free | $0 | The hosted research preview of STORM and Co-STORM, and the MIT-licensed knowledge-storm package for running it yourself. |

Read from https://github.com/stanford-oval/storm on Oct 5, 2026. Prices change, so confirm with STORM before buying.

## Key features

- **Report generation:** Researches a topic through Internet search, drafts an outline and writes a full-length, Wikipedia-like article with citations to its sources.
- **Perspective-guided questions:** Looks for different perspectives on the topic and simulates a conversation between a writer and a topic expert, grounded in sources, to work out which questions to ask.
- **Co-STORM:** A collaborative mode in which the user takes part in a discussion among AI experts, with a moderator that raises questions from information not yet used.
- **Mind map:** Co-STORM keeps a mind map that sorts the collected information into a hierarchy of concepts, updated as the discussion goes on.
- **Open-source Python package:** The knowledge-storm package installs with pip and is MIT-licensed. Language and embedding models are configured through litellm.
- **Pluggable search:** Retrieval modules cover Bing, You.com, Brave, Serper, Tavily, DuckDuckGo, SearXNG and Google search, plus a vector store for grounding on your own documents.

## Good for

- Getting a cited overview of an unfamiliar topic
- The pre-writing stage of a long article or report
- Developers who want an open-source research pipeline to adapt

## Worth knowing

- The hosted site is a research preview with limited safety measures, and its terms warn that reports can contain mistakes.
- Inputs on the hosted site are collected for research and may be distributed under a Creative Commons license.
- The developers say the output is not publication-ready and often needs a significant number of edits.
- Running the open-source package yourself requires your own language model and search API keys.

## Works with

Bing Search, You.com, Brave Search, Serper, Tavily, DuckDuckGo, SearXNG, Azure AI Search

**Tags:** Research, Citations, AI agents, Open source, Self-hostable, Mind mapping

## Alternatives

- [Ai2 Asta](https://toolgpa.com/tools/ai2-asta): AI research assistant for finding papers and analyzing data. [Compare](https://toolgpa.com/compare/ai2-asta-vs-storm)
- [Undermind](https://toolgpa.com/tools/undermind): AI literature search agent that reads hundreds of papers. [Compare](https://toolgpa.com/compare/storm-vs-undermind)
- [Elicit](https://toolgpa.com/tools/elicit): AI research assistant for literature search and systematic reviews. [Compare](https://toolgpa.com/compare/elicit-vs-storm)
- [Perplexity](https://toolgpa.com/tools/perplexity): AI search assistant that answers questions with cited sources. [Compare](https://toolgpa.com/compare/perplexity-vs-storm)
- [Gemini Notebook](https://toolgpa.com/tools/notebooklm): Google's AI research assistant that answers from your own sources. [Compare](https://toolgpa.com/compare/notebooklm-vs-storm)

## Sources

The prices, plans, platforms and features above were read from these pages on Oct 5, 2026:

- https://github.com/stanford-oval/storm
- https://storm.genie.stanford.edu

Page: https://toolgpa.com/tools/storm
Listed by ToolGPA (toolgpa.com).