{"id":"docetl","name":"DocETL","maker":"UC Berkeley EPIC lab","url":"https://www.docetl.org","repo":"ucbepic/docetl","package":"pypi:docetl","summary":"A system for building pipelines that process collections of documents with model operators, from a research group at UC Berkeley.","details":"Pipelines are written in YAML or Python and the optimizer rewrites them. It runs locally against model APIs and is MIT licensed. It is aimed at tasks such as extracting themes or summarising large sets of reports, where each step is a model operation.","open_source":true,"hosted":false,"verified":"2026-11-15","category":"documents","category_name":"Document parsing and extraction","page":"https://modelmoot.com/tools/docetl","reviewed":"2026-11-15","checked":{"at":"2026-11-15T14:03:44.997Z","address_answers":true,"repository":{"at":"2026-11-15T20:20:00.691Z","archived":false,"licence":"MIT","language":"Python","last_change":"2026-11-15T18:18:07.000Z","latest_release":{"tag":"0.3.0","published":"2026-06-17T03:25:51.000Z"}}},"note":"Descriptions are the site's own. Facts under \"checked\" were read automatically from the tool's address and public repository."}