ExtractThinker is an open-source project on GitHub with about 1,602 stars, most recently updated in 2026. ExtractThinker is a document intelligence library that helps large language models extract structured information from documents. It offers an ORM-style interaction model, so developers define the shape of the data they want and let the library handle document loading, splitting, OCR and LLM extraction workflows.
Published on GitHub under the Apache-2.0 license, ExtractThinker has attracted a community of about 1,602 stars, which places it among the more visible open-source AI projects in its niche. Development was still active as of 2026, based on the repository’s latest updates. Because the full source code is public, teams can audit how it works, adapt it to their own stack, and self-host it rather than depending on a closed hosted product.
The repository is tagged with topics including ai, document-image-analysis, document-intelligence, document-parsing, document-processing, which gives a quick picture of where it fits in the open-source AI ecosystem. New users can explore the examples and documentation in the repository to understand the main workflows before integrating it into their own projects, and the public issue tracker shows what the maintainers are actively working on and what the community is asking for.
ExtractThinker is Apache-2.0 open source and free to use; you only pay for any LLM API calls your extraction workflows make.
ExtractThinker is best suited for developers building invoice processing, contract analysis, form extraction and other document automation pipelines on top of LLMs. Anyone evaluating it should start with the GitHub repository, where the documentation, examples and issue tracker show exactly what the current version can do.