{"data":{"slug":"stanford-oval-storm","name":"storm","tagline":"An LLM-powered knowledge curation system for topic research and report generation","github_url":"https://github.com/stanford-oval/storm","owner":"stanford-oval","repo":"storm","owner_avatar_url":"https://avatars.githubusercontent.com/u/13667124?v=4","primary_language":"Python","stars":31433,"forks":2955,"topics":["agentic-rag","deep-research","emnlp2024","knowledge-curation","large-language-models","naacl","nlp","report-generation","retrieval-augmented-generation"],"archived":false,"github_pushed_at":"2025-09-30T18:07:21+00:00","maintenance_label":"Slowing","stars_delta_30d":407,"url":"https://www.graphcanon.com/tools/stanford-oval-storm","markdown_url":"https://www.graphcanon.com/tools/stanford-oval-storm.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/stanford-oval-storm","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=stanford-oval-storm","description":"An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.","homepage_url":"http://storm.genie.stanford.edu","license":"MIT","open_issues":108,"watchers":197,"ai_summary":"STORM is a system that leverages large language models to research a given topic and produce comprehensive reports with citations. It supports customization through its source code and uses different models for various components to balance cost and quality.","readme_excerpt":"## Installation\n\n\nTo install the knowledge storm library, use `pip install knowledge-storm`. \n\nYou could also install the source code which allows you to modify the behavior of STORM engine directly.\n1. Clone the git repository.\n    ```shell\n    git clone https://github.com/stanford-oval/storm.git\n    cd storm\n    ```\n   \n2. Install the required packages.\n   ```shell\n   conda create -n storm python=3.11\n   conda activate storm\n   pip install -r requirements.txt\n   ```\n\n---\n\n# STORM is a LM system so different components can be powered by different models to reach a good balance between cost and quality.\n\n---\n\n## Quick Start with Example Scripts\n\nWe provide scripts in our [examples folder](examples) as a quick start to run STORM and Co-STORM with different configurations.\n\nWe suggest using `secrets.toml` to set up the API keys. Create a file `secrets.toml` under the root directory and add the following content:\n\n```shell","github_created_at":"2024-03-24T16:23:39+00:00","created_at":"2026-07-07T17:33:11.366036+00:00","updated_at":"2026-09-20T04:33:17.995852+00:00","categories":[{"slug":"data-retrieval","name":"Data & Retrieval","url":"https://www.graphcanon.com/categories/data-retrieval","markdown_url":"https://www.graphcanon.com/categories/data-retrieval.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/data-retrieval"},{"slug":"llm-frameworks","name":"LLM Frameworks","url":"https://www.graphcanon.com/categories/llm-frameworks","markdown_url":"https://www.graphcanon.com/categories/llm-frameworks.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/llm-frameworks"}],"tags":[{"slug":"agentic-rag","name":"agentic-rag"},{"slug":"deep-research","name":"deep-research"},{"slug":"emnlp2024","name":"emnlp2024"},{"slug":"knowledge-curation","name":"knowledge-curation"},{"slug":"large-language-models","name":"large-language-models"},{"slug":"naacl","name":"naacl"},{"slug":"nlp","name":"nlp"},{"slug":"report-generation","name":"report-generation"}],"trust":{"provenance":{"is_fork":false,"github_id":776854298,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-18T08:46:46.053Z","maintenance":{"label":"Slowing","score":36,"methodology":"github_public_v1","releases_90d":0,"days_since_push":352,"last_release_at":"2025-01-23T07:21:44Z","stars_delta_30d":407,"open_issues_delta_30d":0},"security_summary":{"status":"ok","scanner":"osv@v1","low_count":0,"high_count":0,"last_scan_at":"2026-09-18T08:46:48.272Z","medium_count":0,"scan_profile":"deps","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-18T08:46:44.978Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-09-18T08:46:44.978Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-09-18T08:46:44.978Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When you need a system that can generate comprehensive reports with citations using large language models.","If you require the flexibility to customize the system's behavior directly through its source code.","For projects that benefit from a balance between cost and quality, as different components can be powered by different models."],"when_not_to_use":["If you are looking for a tool that does not require API keys for its operation, as STORM suggests using API keys for certain functionalities.","When you prefer a system that does not offer the option to modify its behavior through source code, as STORM provides this customization feature."],"source":"enrich:decision_facts","observed_at":"2026-09-18T10:06:48.523Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"STORM is an LLM-powered knowledge curation system that automates topic research and report generation with citations, offering customization through its source code."}]}}