{"data":{"slug":"docling","name":"Docling","tagline":"MIT local document parser that feeds PDFs and Office files into gen-AI pipelines","category":"python","categoryName":"Python","url":"https://docling.ai","github":"https://github.com/docling-project/docling","pricing":"open-source","hook":"Docling turns messy PDFs, Office docs, and more into structured DoclingDocument export (Markdown/JSON/HTML) that agents and RAG stacks can actually use.","whatsGood":"MIT (docling-project/docling). Strong PDF understanding (layout, reading order, tables, code, formulas), wide format coverage, local/air-gapped execution, and gen-AI ecosystem integrations. It is the practical document-ingestion primitive when agents must read real enterprise files, not only clean Markdown.","theCatch":"Vs MinerU and plain OCR pipelines: Docling is the broader multi-format DoclingDocument stack with gen-AI export paths — still expect GPU/CPU cost on heavy PDF batches and imperfect table recovery on ugly scans. Local models and extras increase install weight versus a thin Markdown converter.","verdict":"MIT document AI for agent/RAG ingest. Default when PDFs and Office files must become structured context locally.","addedAt":"2026-09-20","featured":false,"domain":"Python","subSpecialty":"Document AI","subcategory":"Document AI","tags":["self-host","permissive","rag","active","fast-stars"],"capabilities":["pdf","rag","parsing"],"surfaces":["Self-host"],"ecosystem":["Python","Multi-platform"],"licenseModel":"OSS/MIT","githubStars":69085,"starsPerWeek":581,"access":"free","archived":false,"repo":{"createdAt":"2024-07-09","pushedAt":"2026-10-18","license":"MIT","archived":false,"checkedAt":"2026-10-19"}},"related":[{"slug":"fastapi","name":"FastAPI","tagline":"Modern Python APIs at startup speed"},{"slug":"pydantic","name":"Pydantic","tagline":"Data validation using Python type hints"},{"slug":"uv","name":"uv","tagline":"Python packaging at Rust speed"},{"slug":"ruff","name":"Ruff","tagline":"Python linter faster than your test suite"},{"slug":"polars","name":"Polars","tagline":"DataFrames that respect your CPU"}],"links":{"self":"/api/gems/docling","html":"/gems/docling","markdown":"/gems/docling.md","category":"/api/gems?category=python","categoryPage":"/stacks/python"}}