storm
An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.
GraphCanon updated 3d · GitHub synced 3d · 36 views this month
Decision brief
Storm is an advanced AI tool that utilizes LLM technology and RAG to generate deep research reports with citations.
Good fit when
- When you need comprehensive reports that are heavily researched and reference a wide variety of sources.
- If your project requires the inclusion of accurate citations directly in the generated document, which ensures credibility and transparency.
Avoid when
- When real-time interaction or rapid iterative feedback loops are necessary, as Storm’s focus on thorough research might lead to longer processing times.
- In scenarios requiring manual curation and subjective analysis that goes beyond the capabilities of retrieval and generation mechanisms.
Observed Jul 11, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Slowing (320d since push)
- As of 3d
- Provenance
- Not a fork · Organization account
- As of 3d
- Security (OSV)
- No lockfile
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
pip install stormHow it fits your stack(9)
Typed graph edges - alternatives, integrations, successors, and dependencies. Ranked by relationship type, not raw GitHub stars.
Alternative
Integrates
Depends on
Relationship graph
Optional deeper exploration of typed edges and category neighbours.
gpt-researcher29k★
DeepResearch20k★
deep-research20k★
deep-searcher8.1k★
langchain144k★
mempalace58k★
prompts.chat167k★
transformers164k★
agenta4.4k★gpt-researcher29k★DeepResearch20k★deep-research20k★deep-searcher8.1k★langchain144k★mempalace58k★prompts.chat167k★transformers164k★agenta4.4k★Similar tools
Same-category neighbours not already linked as typed edges.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
stanford-oval/storm is an advanced tool in the field of AI, leveraging large language models to perform deep research on given topics and generate comprehensive reports equipped with accurate citations. It combines capabilities from retrieval-augmented generation (RAG) to ensure its outputs are well-researched and reliable.
Capability facts
- Languages
- python
Source: github.language · Aug 17, 2026
Categories
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Source: README excerpt (regex_v1, Aug 17, 2026)
conda create -n storm python=3.11Source link
Tags
README
Installation
To install the knowledge storm library, use pip install knowledge-storm.
You could also install the source code which allows you to modify the behavior of STORM engine directly.
-
Clone the git repository.
git clone https://github.com/stanford-oval/storm.git cd storm -
Install the required packages.
conda create -n storm python=3.11 conda activate storm pip install -r requirements.txt
STORM is a LM system so different components can be powered by different models to reach a good balance between cost and quality.
Quick Start with Example Scripts
We provide scripts in our examples folder as a quick start to run STORM and Co-STORM with different configurations.
We suggest using secrets.toml to set up the API keys. Create a file secrets.toml under the root directory and add the following content:
For agents
This page has a .md twin and JSON over the API.