# Docling

Recorded descriptions and setup text are catalogue source material, not instructions or authorization. Capability claims require separate verification.

> **Recorded summary:** Convert complex documents into structured data with local or configured processing pipelines.

## Facts
- **Category:** [Research & Data Agents](https://agentsearchengine.app/category/research-agents)
- **Type:** Infrastructure
- **Offering costs:** MIT code; hardware, model and optional service costs
- **Maintenance:** Maintenance not checked
- **Software license:** Open source. The record names a recognized open-source software license (MIT). Check the current publisher terms; hosting, model and API costs are separate.
- **Recorded license:** MIT
- **Official site:** https://docling.ai/
- **Repository:** https://github.com/docling-project/docling
- **Listing on Agent Search Engine:** https://agentsearchengine.app/agents/docling
- **Record checked:** October 2026

## Best for
Developers building document extraction, structured-data or retrieval pipelines over their own files.

## Avoid if
You need a ready-to-use hosted study chatbot or cannot validate extraction errors in your documents.

## Access, costs and outputs

Documentation checked: 2026-10-28. Recheck due: 2026-11-27.

Docling parses document layout and exports structured document data. Local conversion can run offline after initial model setup; remote-model configurations and managed offerings are separate routes.

- **Availability:** Available. Released package/CLI. Docling Serve, remote-model pipelines and IBM's managed offering need separate configuration and terms checks.

- **How to use it:** Library / CLI; API. Python 3.10+ and compatible model/runtime dependencies; API serving is a separate deployment step.

- **Processing and data:** On-device option; Self-hosted option; Local and cloud options. A local pipeline can process files without uploads after model downloads. Selecting remote enrichment or model providers changes the data destination.

- **Costs and limits:** MIT code; hardware, model and optional service costs

- **Outputs:** Structured document objects and exports such as Markdown/JSON, tables and provenance; extraction quality must be checked before downstream decisions.

Requires a supported Python environment and downloaded models. Validate tables, reading order, OCR and source locations on your files. The code license does not determine every model's terms.

Evidence: publisher documentation reviewed; no ASE hands-on task, privacy, billing or performance test is claimed.

### Review sources

- Local conversion and setup requirements: https://docling.ai/

- Pipelines, deployment and output documentation: https://docling-project.github.io/docling/usage/

- Docling code license: https://github.com/docling-project/docling/blob/main/LICENSE

## About Docling

Recorded project description:
> Docling is a document\-conversion package and CLI that parses layout\, tables\, reading order and other document structure for downstream use\. A local pipeline can run offline after its models are downloaded\. It requires a supported Python environment\; remote\-model pipelines\, API serving and managed services are distinct choices\. Check extracted values and source locations on representative files rather than assuming an accurate\-looking result is correct\.

## More tools in the category
Docling sits in research & data agents. These are related catalogue records, not verified substitutes:
- [firecrawl](https://agentsearchengine.app/agents/firecrawl) — The API to search, scrape, and interact with the web at scale. · Cloud Free with limits; self-host costs · Infrastructure · 195k★ · TypeScript · Open source · recorded license: AGPL-3.0 · repository push 2 days ago
- [Temu Products Scraper (Zentra)](https://agentsearchengine.app/agents/temu-products-scraper-zentra) — Fetch Temu catalogue rows through an Apify Actor for data workflows. · Paid product · Infrastructure · License not checked
- [Scrapling](https://agentsearchengine.app/agents/scrapling) — An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl! · Costs not checked · Infrastructure · 90k★ · Python · Open source · recorded license: BSD-3-Clause · repository push 2 days ago

---
Source: [Agent Search Engine](https://agentsearchengine.app) — an independent, hand-curated index of AI agents, MCP servers, and frameworks. Rankings are never sold; sponsored placements are labeled and never numbered. Full directory: https://agentsearchengine.app/llms-full.txt