{"id":"chunkr","name":"Chunkr","maker":"Lumina","url":"https://www.chunkr.ai","repo":"lumina-ai-inc/chunkr","package":"pypi:chunkr-ai","summary":"A document ingestion service that splits files into chunks with layout-aware parsing, offered as an API and for self-hosting.","details":"It turns PDFs and other files into segments labelled by type, with OCR and optional model-based cleanup. The code is under the AGPL licence and can be run from containers. A hosted API also exists.","open_source":true,"hosted":true,"verified":"2026-11-15","category":"documents","category_name":"Document parsing and extraction","page":"https://modelmoot.com/tools/chunkr","reviewed":"2026-11-15","checked":{"at":"2026-11-15T13:03:28.711Z","address_answers":true,"repository":{"at":"2026-11-15T18:16:59.395Z","archived":false,"licence":"AGPL-3.0","language":"Rust","last_change":"2026-09-09T22:54:07.000Z","latest_release":{"tag":"v2.2.1","published":"2025-07-31T20:29:25.000Z"}}},"note":"Descriptions are the site's own. Facts under \"checked\" were read automatically from the tool's address and public repository."}