{
  "data": null,
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/niches/document-extraction.private-local-parse/",
    "json": "https://www.anchorterminal.com/niches/document-extraction.private-local-parse/index.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/niches/document-extraction.private-local-parse/index.md",
    "mcp": "https://www.anchorterminal.com/mcp",
    "slim": "https://www.anchorterminal.com/niches/document-extraction.private-local-parse/index.min.md"
  },
  "markdown": "Two or three companies' docs show a full fit.\n\n| Companies, full fit | With a limit | Carry the tag | Share of the category's work | First-hand accounts |\n| --- | --- | --- | --- | --- |\n| 2 | 9 | 113 | 8 | 5 |\n\n## What counts as done\n\nThe tool runs on the stated hardware with a documented install, gives the same output as its hosted version where one exists, and the docs state retention, deletion and whether inputs train models.\n\nHow agents ask for it: parse these locally, they can't leave the machine; which parser can I self-host; run OCR on my own GPU\n\n## Does the job\n\nThe docs show it meets the test above, and nothing we read says otherwise.\n\n- **Docling (Docling Project (LF AI \u0026 Data Foundation))**: MIT-licensed library that runs locally on macOS, Linux and Windows, x86_64 and arm64, with a documented CPU-only torch install; there is no hosted version to differ from. acc-18's Windows install failure predates the current install page.\n- **Xiaomi-OCR-0 (Xiaomi Corporation)**: Apache 2.0 weights with a documented install; the example code falls back to CPU in float32, and community GGUF builds exist. There is no hosted version to differ from.\n\n## Does the job, with a limit\n\nIt does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.\n\n- **Azure Document Intelligence (Microsoft Corporation)**: Read and Layout v4.0 containers run on 8 CPU cores with 10 to 24 GB, but they must send billing data to an Azure endpoint, and hosted inputs are kept 24 hours with a delete call.\n- **Datalab (Endless Labs, Inc.)**: Marker, Surya and Chandra weights are free under $2M to $5M revenue thresholds, and acc-14 rated Marker best to self-host, but the supported on-prem container needs an Enterprise contract.\n- **Extend API + MCP (CrowdView Inc. dba Extend)**: BYOC deploys into the customer's own cloud VPC and zero retention is available on request, with no training by inference providers, but there is no laptop or single-GPU install with stated hardware.\n- **Invofox (Invofox, Inc. (Delaware), with a registered branch in Spain)**: The vendor briefing claims on-premises and VPC deployment and an opt-in zero-retention mode, but no install docs or hardware are published, and corrections feed model training.\n- **LlamaParse API + MCP (LlamaIndex, Inc.)**: Self-hosted LlamaCloud runs on Kubernetes through a Helm chart on Enterprise plans only, and still calls OpenAI, Anthropic or Google models, so documents leave the cluster unless enterprise cloud models are set up.\n- **Nanonets API + MCP (Nano Net Technologies Inc.)**: The open-source docstrange library runs locally, but acc-41 found local output much worse than the hosted version.\n- **Nemotron 3.5 Parse (NVIDIA Corporation)**: Open weights under OpenMDW-1.1 with documented Transformers and vLLM serving, but the model is built for NVIDIA GPUs with no CPU path documented.\n- **Reducto API + MCP (Reducto, Inc.)**: Dedicated VPC and on-prem deployments are documented with their own changelog and security model, but they are enterprise contracts, and zero data retention is Growth and Enterprise only.\n- **Unstructured API + MCP (Unstructured Technologies, Inc.)**: The open-source library installs with pip or runs from multi-platform Docker images for x86_64 and Apple silicon, but CPU and GPU requirements and any differences from Transform's output are not documented in the README.\n\n## Couldn't check\n\nThe docs were closed to us, or silent. These carry no mark either way.\n\n- **Veryfi API + MCP (Veryfi, Inc.)**: No self-hosted option appears in the SDK README, and the retention and training pages were not re-read this pass.\n\n- not this job: Adobe PDF Services / PDF Extract API (Adobe Inc.): Hosted only. Assets are kept 24 hours with a delete endpoint, but nothing runs on the user's machine.\n- not this job: Amazon Textract (Amazon Web Services, Inc.): Hosted AWS service only; no self-hosted path.\n- not this job: Clairic (Cloudflare, Inc.): Hosted on Workers AI only; open weights are promised with no date. The model page does state zero data retention.\n- not this job: Google Cloud Document AI (Google LLC): Hosted Google Cloud service only; no self-hosted processor.\n- not this job: LandingAI Agentic Document Extraction (LandingAI, Inc.): Hosted in the US or EU only; the docs index lists no self-hosted or on-premises install. Zero Data Retention is a Team and Enterprise setting.\n- not this job: Mindee API (Mindee SAS (Mindee Inc. outside the Eurozone)): Hosted only. Extracted data is kept 12 hours by default (24 at most), the original file is never stored to disk, and processing can be pinned to the EU.\n- not this job: Mistral OCR API (Mistral AI (RCS Paris 952 418 325)): Hosted API only; no self-hosted OCR model in the docs read. Zero data retention is available to eligible organisations.\n- not this job: OpenDocRouter (LlamaIndex, Inc.): Hosted router only. Without cache nothing is stored, and cached results last 24 hours with a DELETE, but pages go to third-party model providers.\n\n6 listings in the category were added after this reading and aren't marked yet.\n\n## What stops agents finishing\n\n- needs a CUDA GPU the user lacks\n- local model weaker than the hosted one with the same name\n- parsed output kept by the vendor with no delete\n\n## Around it\n\nBefore: file-storage.agent-upload. After: vector-search.local-embedded, document-extraction.rag-ingest.\n\n## Where this comes from\n\nWeight 8 of 100 in Document parsing \u0026 extraction: 5 of 46 accounts (Docling, Marker, docstrange, LlamaParse retention); the Docling and Nemotron listings are built for it\n\nAs data: https://www.anchorterminal.com/api/v1/use-cases/document-extraction.private-local-parse.json, or the MCP tool get_use_case with id document-extraction.private-local-parse. Draft, read 2026-11-15 from public docs and first-hand accounts, not yet reviewed by a person.\n",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "attributionRequired": true,
    "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-11-16",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.8",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run",
    "terms": "https://www.anchorterminal.com/terms/#data"
  },
  "page": {
    "breadcrumbs": [
      {
        "name": "Home",
        "url": "https://www.anchorterminal.com/"
      },
      {
        "name": "For agents",
        "url": "https://www.anchorterminal.com/agents/"
      },
      {
        "name": "Niches",
        "url": "https://www.anchorterminal.com/niches/"
      },
      {
        "name": "Parse documents without sending them out",
        "url": ""
      }
    ],
    "description": "Parse documents without sending them out: 2 companies fully do it, 9 with a limit, 113 carry the tag. Every listing in Document parsing \u0026 extraction with the reason and a source.",
    "facts": null,
    "h1": "Parse documents without sending them out",
    "image": "https://www.anchorterminal.com/assets/og/default.png",
    "path": "/niches/document-extraction.private-local-parse/",
    "published": "",
    "section": "agents",
    "title": "Parse documents without sending them out | Anchor Terminal",
    "toc": null,
    "updated": "2026-11-15",
    "url": "https://www.anchorterminal.com/niches/document-extraction.private-local-parse/"
  },
  "tokens": {
    "markdown": 1650,
    "slim": 330
  },
  "version": 1
}
