Workflows · Skill

STORM

STORM explores a topic from multiple perspectives, then uses the resulting outline and references to draft a cited article.

+ Follow

Builder facts

  • Research loop. Prewriting surveys related articles for perspectives and simulates exchanges with a source-grounded expert to generate follow-up questions. Source ↗
  • Drafting. The writing stage uses the outline and collected references to produce an article with citations. The project describes the result as a draft that needs editing for publication. Source ↗
  • Configuration. The knowledge-storm Python package exposes model and retriever settings. The documented example uses separate OpenAI and You.com credentials. Source ↗
  • Co-STORM. The related runner lets people steer the research conversation and organizes the findings in an evolving mind map. Source ↗
  • Access. The source is MIT-licensed. Running the documented example uses the configured model and search providers under their own terms. Source ↗

Sources checked

Publisher update ·

STORM 1.1.0 adds LiteLLM support ↗

The release added LiteLLM model compatibility to STORM and Co-STORM, and added Azure AI Search as a retriever.

Change timeline

0 stories

No verified releases in this timeline yet.