{
  "slug": "docling",
  "name": "Docling",
  "category": "Tools / Document Ingest",
  "tagline": "Turn PDFs, Office docs, Apple iWork files, audio and more into clean Markdown/JSON for RAG.",
  "kit_says": "Garbage in, garbage out. Docling is how I'd feed a local model documents it can actually reason over.",
  "homepage": "https://github.com/docling-project/docling",
  "repo": "https://github.com/docling-project/docling",
  "docs": "https://docling-project.github.io/docling/",
  "license": "MIT",
  "platforms": [
    "macos-apple-silicon",
    "linux",
    "windows"
  ],
  "mac_studio_fit": "Primary",
  "what_it_is": "A document conversion toolkit (Python package and CLI) that parses many formats into structured output for gen-AI pipelines.",
  "gap_role": "Retrieval quality: better parsing, better RAG answers from local models.",
  "prerequisites": [
    "Python 3.10+ (3.9 support dropped in 2.70.0)"
  ],
  "install": {
    "macos-apple-silicon": [
      {
        "run": "python3 -m venv ~/.venvs/docling && source ~/.venvs/docling/bin/activate"
      },
      {
        "run": "pip install docling"
      }
    ],
    "linux": [
      {
        "run": "pip install docling"
      }
    ],
    "windows": [
      {
        "run": "pip install docling"
      }
    ]
  },
  "configure": [
    {
      "run": "docling --pipeline vlm --vlm-model granite_docling https://arxiv.org/pdf/2206.01062",
      "note": "optional: VLM pipeline using GraniteDocling"
    }
  ],
  "verify": [
    {
      "run": "docling https://arxiv.org/pdf/2206.01062",
      "expect": "writes a Markdown conversion of the paper to the current directory"
    }
  ],
  "rollback": [
    {
      "run": "pip uninstall -y docling && rm -rf ~/.venvs/docling"
    }
  ],
  "caveats": [
    "First run downloads layout models."
  ],
  "works_with": [
    "mem0",
    "open-webui"
  ],
  "sources": [
    "https://github.com/docling-project/docling"
  ],
  "sponsored": false,
  "verified_on": "2026-10-15",
  "gap_score": {
    "value": null,
    "status": "pending test on Mac Studio",
    "baseline": "frontier reference (see /about#gap-score)"
  },
  "benchmarks": {
    "status": "pending test on Mac Studio",
    "rig": "Mac Studio, Apple Silicon, 128GB unified memory",
    "results": []
  },
  "hardware_tested": [],
  "repo_meta": {
    "stars": 68929,
    "stars_as_of": "2026-10-15",
    "last_push": "2026-10-15",
    "archived": false,
    "license_spdx": "MIT"
  },
  "stack_layer": "memory",
  "summary": {
    "what": "Turns documents into clean text for AI.",
    "why": "Better input means better answers from your docs."
  }
}