In simple English
This tool searches the internet for information on any topic you choose. It asks questions from different angles to gather deep details. Then it organizes the facts and writes a full-length report with citations. You need your own paid API keys for language models and search engines to make it work. It helps you explore unfamiliar subjects quickly without writing everything by hand.
What it is
STORM (Synthesis of Topic Outlines through Retrieval and Multi-perspective Question Asking) is a Python library from Stanford University for automated research and report writing. It simulates conversations between a writer and an expert to uncover deep insights before drafting a structured article.
What it is good for
Solo builders and researchers who want to generate comprehensive background reports or kickstart writing projects without spending hours on manual web research.
- Produces thorough articles complete with source citations.
- Supports multiple search engines including Bing, You.com, and Tavily.
- Allows human-in-the-loop collaboration to steer the research direction.
- Requires paid API keys for language models and search providers.
- Setting up Python environments and configuration files takes moderate technical effort.
- Generated reports still require human editing to ensure complete accuracy.
Manual web searches and drafting long-form background research reports from scratch
LangChain (a software library for building applications with language models)
- assafelovic/gpt-researcher30k stars
Another autonomous agent that scours the web to compile comprehensive research reports.
- ggml-org/llama.cpp132k stars
A C and C++ library and command-line tool for running language models locally.
- EleutherAI/lm-evaluation-harness14k stars
Runs standard question sets against a language model and reports the scores.
- mudler/LocalAI50k stars
Serves text, vision, speech, image and video models from one self-hosted service that imitates the paid interfaces.
git clone https://github.com/stanford-oval/storm.git cd storm conda create -n storm python=3.11 conda activate storm pip install -r requirements.txt