STORM vs Undermind

STORM

• 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

Undermind

• Complex research questions where keyword search misses relevant papers
• Academics, who pay $16 a month on annual billing instead of the $60 industry rate
• People who want literature search inside Claude, ChatGPT or a coding agent
• R&D teams tracking new publications in specific technical areas

STORM

• 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.

Undermind

• Free-tier searches read abstracts and metadata only; full-text search of open-access papers and preprints needs Pro.
• Industry pricing is far higher than academic: Pro is $60 a month billed annually against $16.
• A deep search typically takes about 2 minutes to finish, so results are not instant.
• Charges are non-refundable once a billing period has begun, except where the law requires a refund.

STORM

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.

Undermind

Deep literature search

You describe a research goal in plain language and answer follow-up questions. Undermind then reads and evaluates hundreds of papers and follows citation trails; a typical search takes about 2 minutes.

Reports with in-line citations

Findings come back as a report in which statements carry in-line citations that lead to the source paper, alongside a paper list you can sort and filter to judge relevance.

Chat and custom tables

After a search you can brainstorm with an assistant grounded in the papers it found, extract details from full texts and generate custom tables.

Alerts for new papers

Undermind keeps track of your areas of interest and notifies you when relevant papers are published.

Agent connections over MCP

An MCP server lets assistants and coding agents such as Claude, ChatGPT, Cursor and VS Code run Undermind searches. Connecting agents is included in the Free plan.

Full-text search on Pro

The Free tier searches abstracts and metadata. Pro adds compute to search the full texts of nearly all open-access and preprint articles.

STORM

• Free$0

  The hosted research preview of STORM and Co-STORM, and the MIT-licensed knowledge-storm package for running it yourself.

Undermind

• Free$0

  Chat, deep searches and reports with standard rate limits, shared workspaces and agent connections over MCP.

• Pro (Academic)$16

  per month, billed annually ($192); $20 billed monthly

  The newest AI models, full-text analysis, 10x higher usage limits, and unlimited workspaces, files and paper libraries.

• Pro (Industry)$60

  per month, billed annually ($720); $75 billed monthly

  The same Pro features at the industry rate.

• Team (Academic)$15

  per person / month, billed annually; $18.70 billed monthly

  From 3 seats. Pro features plus member management, priority support and central billing. Falls to $12.50 per person at 60 or more seats.

• Team (Industry)$60

  per person / month, billed annually; $75 billed monthly

  From 3 seats at the industry rate, with member management, priority support and central billing.

• EnterpriseCustom

  Increased compute, sitewide organizational login, an admin dashboard, onboarding seminars, and custom terms, SLA and security review.

STORM

No public discounts listed.

Undermind

• Annual discount

  Save 20% with annual billing

  Pro is $16 a month billed annually against $20 billed monthly at the academic rate, and $60 against $75 at the industry rate. The pricing section labels this a 20% saving.

• Education

  Academic pricing from $16 a month

  Choosing Academic in the pricing section shows Pro at $16 a month billed annually or $20 billed monthly, against $60 and $75 under Industry.

• Other savings

  Volume pricing on academic Team plans

  On annual billing the academic Team price per person is $15 for 3 to 10 seats, $14.17 for 11 to 25, $13.33 for 30 to 50 and $12.50 for 60 to 200.