Niches · Document parsing & extraction
Parse documents without sending them out
Two or three companies' docs show a full fit.
What counts as done
The 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.
How 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
Does the job 2
The docs show it meets the test above, and nothing we read says otherwise.
| Listing | Why |
|---|---|
| Docling B Docling Project (LF AI & 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. source |
| Xiaomi-OCR-0 C 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. source |
Does the job, with a limit 9
It 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.
| Listing | Why |
|---|---|
| Azure Document Intelligence B 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. source |
| Datalab B 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. source |
| Extend API + MCP B 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. source |
| Invofox D 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. source |
| LlamaParse API + MCP B 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. source |
| Nanonets API + MCP E Nano Net Technologies Inc. | The open-source docstrange library runs locally, but acc-41 found local output much worse than the hosted version. source |
| Nemotron 3.5 Parse B 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. source |
| Reducto API + MCP B 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. source |
| Unstructured API + MCP E 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. source |
Couldn't check 1
The docs were closed to us, or silent. These carry no mark either way.
| Listing | Why |
|---|---|
| Veryfi API + MCP C Veryfi, Inc. | No self-hosted option appears in the SDK README, and the retention and training pages were not re-read this pass. |
Doesn't do this job 8
Listings in the category that do something else, with the reason.
| Listing | Why |
|---|---|
| Adobe PDF Services / PDF Extract API C Adobe Inc. | Hosted only. Assets are kept 24 hours with a delete endpoint, but nothing runs on the user's machine. source |
| Amazon Textract BB Amazon Web Services, Inc. | Hosted AWS service only; no self-hosted path. source |
| Clairic BB Cloudflare, Inc. | Hosted on Workers AI only; open weights are promised with no date. The model page does state zero data retention. source |
| Google Cloud Document AI BB Google LLC | Hosted Google Cloud service only; no self-hosted processor. source |
| LandingAI Agentic Document Extraction BB 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. source |
| Mindee API C 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. source |
| Mistral OCR API B 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. source |
| OpenDocRouter B 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. source |
6 listings in the category were added after this reading and aren't marked yet.
What stops agents finishing
- needs a CUDA GPU the user lacks
- local model weaker than the hosted one with the same name
- parsed output kept by the vendor with no delete
Around it
Before: file-storage.agent-upload. After: vector-search.local-embedded, document-extraction.rag-ingest.
Where this comes from
Weight 8 of 100 in Document parsing & extraction: 5 of 46 accounts (Docling, Marker, docstrange, LlamaParse retention); the Docling and Nemotron listings are built for it
The same as data: /api/v1/use-cases/document-extraction.private-local-parse.json, or the MCP tool get_use_case with id document-extraction.private-local-parse. Other jobs in this category: /api/v1/niches?category=document-extraction.
For companies
Do agents find, use and choose your tools?
An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.