🔴 Advanced ⚙️ Type: Autonomous AI Research Agent 💸 Free & Open Source (MIT) ⭐ 16,000+ GitHub Stars
What is STORM?
STORM (Synthesis of Topic Outlines through Retrieval and Multi-perspective Question Asking) is a groundbreaking autonomous research system built by the Stanford Open Virtual Assistant Lab (OVAL). While standard LLMs like ChatGPT often hallucinate or provide shallow summaries when asked to “write a report,” STORM is engineered to produce full-length, Wikipedia-grade articles from scratch, complete with comprehensive citations.
Instead of just blindly searching the internet, STORM completely re-engineers the pre-writing phase of research. When you give it a topic, it automatically identifies 6 to 8 different “perspectives” (e.g., a historian, an economist, a technologist). It then spawns multiple AI agents that simulate an expert interview—the “writer” asks deep, probing questions, and the “expert” answers by searching the live internet.
The newest version includes Co-STORM, which allows a human user to jump into the middle of the agent debate, guiding the research direction before the AI curates the final outline and drafts the fully-grounded, hallucination-free document.
Who is it for?
- Academics & PhD Students looking to rapidly generate thorough literature reviews and heavily-cited background reports before starting their own original writing.
- Technical Writers & Journalists who need deep-dive briefings on complex new technologies (like quantum computing or new AI models) that gather multiple viewpoints automatically.
- AI Developers interested in learning how to build multi-agent orchestration frameworks and Retrieval-Augmented Generation (RAG) pipelines that enforce strict factual grounding.
What makes it special?
- Perspective-Guided Discovery — It doesn’t just ask “What is X?” It simulates the brain of different experts. If researching a new drug, the AI will ask questions from the perspective of a patient, a pharmaceutical executive, and a regulatory lawyer, ensuring the final article has incredible breadth.
- Strict Citation Grounding — Every single claim generated in the final report is tied back to a specific URL discovered during the research phase. It actively minimizes hallucination by refusing to write facts it cannot find a source for.
- Modular Architecture (DSPy) — Built heavily upon the DSPy framework, STORM allows you to swap out its internal engine. You can use GPT-4o for the writing agent, Claude 3.5 Sonnet for the outlining agent, and Bing or Tavily for the search retriever.
Requirements before you start
Because STORM is a multi-agent backend pipeline, you will need to run it via the terminal or Python scripts:
- Python 3.11 — The required version for the current codebase (a Conda environment is highly recommended).
- Search API Key — You need a search engine for the agents to use. Bing Search API, Tavily, or You.com are natively supported.
- LLM API Keys — You need an active API key for OpenAI (GPT-4o), Anthropic, or an Azure OpenAI endpoint. (Note: Using local Ollama models is possible but difficult due to the complex reasoning required by the agents).
Step-by-step installation
The easiest way to get STORM running locally is by cloning the official repository and running the provided runner scripts.
Step 1 — Clone the Repository and Setup Environment
Open your terminal, clone the codebase, and create a fresh Conda environment using Python 3.11:
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.txtStep 2 — Configure API Keys
STORM manages credentials using a secrets file. Create a new file named secrets.toml in the root directory and add your keys. For example, if you are using OpenAI and Tavily for search:
OPENAI_API_KEY="sk-proj-your-openai-key"
OPENAI_API_TYPE="openai"
TAVILY_API_KEY="tvly-your-tavily-key"Step 3 — Run the STORM Pipeline
You can execute the pipeline directly from the command line using the provided demonstration script. We will tell it to use Tavily for search and GPT-4o for writing:
python scripts/run_storm.py \
--topic "The history and impact of open-source AI" \
--retriever tavily \
--lm-type openai \
--engine-model gpt-4oSit back and watch the terminal. The agents will begin talking to each other, searching the web, evaluating sources, generating an outline, and finally writing the article. The final Markdown file (along with the references and conversation logs) will be saved in the generated output folder.
Common errors and fixes
| Error | What it means | How to fix it |
|---|---|---|
| Massive API Token Costs | Because STORM simulates an ongoing multi-turn interview between agents while feeding them massive amounts of scraped website text, it consumes a tremendous amount of input tokens. | If running the pipeline frequently, swap the heavy engine models (like GPT-4o) out for faster, cheaper models like gpt-4o-mini or claude-3-5-haiku for the question-asking and outlining phases. |
| Search API Rate Limits Hit | The expert agent tried to perform too many Google/Bing searches per minute, triggering a block from your search provider. | Upgrade your Tavily or Bing Search API tier from the “Free” tier to a paid tier. A single STORM article generation can execute dozens of complex search queries in seconds. |
DSPy Configuration Error or Missing Imports | You are likely running a Python version older than 3.11, or the DSPy library updated and broke backwards compatibility with Stanford’s code. | Ensure you strictly followed the Conda python=3.11 requirement. If issues persist, run pip install knowledge-storm instead of running the raw source code from GitHub, as the PyPI package is more rigorously version-locked. |
Free vs Paid comparison
| Feature | STORM (Stanford Open Source) | Perplexity Pro / Google Deep Research |
|---|---|---|
| Cost | 🟢 Free software (Pay only for raw API tokens) | 🔴 Approx $20/mo Subscription |
| Research Depth | 🟢 Phenomenal (Simulates multi-perspective interviews) | ⚠️ High, but often lacks the specific “Wikipedia structure” |
| Human-in-the-Loop | ✅ Yes (via Co-STORM interface) | ❌ Fully automated black-box |
| Customization | 🟢 Total control over which LLMs and Search APIs are used | 🔴 Locked into the provider’s ecosystem |
Bottom line: Stanford’s STORM is arguably the most impressive open-source research agent available today. It proves that simply prompting an LLM with “write a good article” is the wrong approach. By forcing the AI into a strict workflow of perspective-gathering, interviewing, and outlining before a single word of the final article is written, STORM generates content that rivals human analysts. If you need heavily-cited, academic-grade research, this is the tool to install.
Alternatives — 3 similar tools
1. GPT Researcher
The most popular direct competitor to STORM. GPT Researcher also spawns multiple autonomous agents to scrape the web and write detailed reports. However, GPT Researcher is generally easier to install, has a better out-of-the-box web UI, and supports a wider variety of export formats (PDF, Word, etc.) natively, though STORM’s academic perspective-gathering is slightly more rigorous.
🔗 github.com/assafelovic/gpt-researcher
2. Perplexity Pro (Deep Research)
If you don’t want to mess around with Python environments or API keys, Perplexity Pro is the commercial standard. Its “Pro Search” and newly integrated Deep Research features perform similar multi-step web scraping and citation generation inside a flawless, consumer-friendly web application.
3. OpenPerplex
A fast, open-source alternative to Perplexity. While it does not generate massive, multi-page Wikipedia articles like STORM, it is an excellent tool for quick, fully-cited answers to complex questions, combining Groq’s lightning-fast inference with local search retrieval.
🔗 github.com/YassineFadali/OpenPerplex
🚀 Want more free AI tools like this?
We find, test, and write setup guides for the best free and open-source AI tools — so you don’t have to dig through GitHub yourself.Browse Free AI Tools at globalaiforce.com/shop →
📸 Follow us for daily AI tool tips and tutorials: instagram.com/globalaiforce