SuperAPI AI Directory

DocumentCloud

DocumentCloud is an open-source, one-stop document processing platform for newsrooms and journalists, used to process source documents. Users can upload and organize files, perform full-text search, optical character recognition, text extraction and analysis, and can also annotate, redact, and edit documents, and embed them into websites. The platform provides a public document library, which currently contains more than 7.24 million public documents, and anyone can browse and organize files of interest into projects. News organizations, independent journalists, archives, and academic projects can upload, annotate, and publish documents; before use, they need to create a MuckRock account and apply for verification. DocumentCloud provides a public API and Python SDK, supports managing large-volume projects, and can use community extensions and tools to further process documents and data. The platform is an open-source project operated by the MuckRock Foundation, dedicated to trust, transparency, and civic engagement.

Open website

About this tool

DocumentCloud is a one-stop platform for newsrooms and journalists, mainly used to process source documents, helping users upload, analyze, and embed documents.

  1. Main uses DocumentCloud serves news organizations, independent journalists, archives, and academic projects for uploading, annotating, and publishing documents, while also allowing the public to explore the public document archive and organize files of interest into projects. The platform currently contains more than 7,241,714 public documents.

  2. Main capabilities

  3. Upload and organize documents.

  4. Extract, analyze, and search text.

  5. Annotate, redact, and edit documents.

  6. Embed documents into your own website.

  7. Automatic optical character recognition and search indexing to facilitate document exploration.

  8. Provide a public API that can be used to manage large-volume projects.

  9. Provide a Python SDK for automating document upload, analysis, and processing tasks.

  10. Community-written extensions and tools can help users further process documents and data.

  11. How to use To get started, you need to create a MuckRock account and apply for verification. After that, you can upload, annotate, and publish documents. If you need automation or to manage large-scale projects, you can use the public API or Python SDK.

  12. Applicable scenarios Suitable for newsrooms processing source files in investigative reporting, journalists and independent news workers organizing, analyzing, and publishing documents, archives and academic projects preserving and publishing materials, and individuals or organizations hoping to engage civically around government transparency. Users can also browse the public document archive and organize files into projects.

  13. Limitations and notes The platform is an open-source project, with code available on GitHub, and is a project of the MuckRock Foundation (a 501c3 organization), which is dedicated to trust, transparency, and civic engagement. All users must comply with the website's privacy policy and terms of service. The platform displays some popular documents, such as Reform UK - Investigation Report - 7 October 2026, TSC 2026.09.30 Emergency Halt and Stay Motion Fowler, 2026.09.30 Emergency Halt and Stay Motion, ACT 2026 Fiscal Plan, CALL 01 - Conversation Redacted. For more information about fees, pricing, or specific usage steps, the materialsNot yet provided.