Extract text from any document on UK hardware. No LLM touches your data during text extraction. Deterministic, auditable, sovereign.
Upload a document. Choose a mode. Get results instantly.
Text extraction and visual description are separate paths. OCR output never touches the vision model.
pdfplumber for text-based PDFs. PaddleOCR for scanned documents and images. python-docx for Word documents. Every character comes directly from the source. No LLM involved.
Gemma 4 vision model for describing diagrams, photos, screenshots, and charts. The only path that uses an LLM. Completely separate from OCR.
From single-page receipts to 200-page contracts.
AWS Textract, Google Vision, and Azure Document Intelligence are operated by US companies. The CLOUD Act gives US authorities the legal power to compel access to your documents.
From invoices to blueprints. Every document processed on sovereign infrastructure.
Extract line items, totals, VAT, and supplier details from invoices and receipts for automated accounting workflows.
Pull clauses, dates, parties, and obligations from contracts for legal review. Handle multi-column layouts and annexes.
Convert paper medical records, prescriptions, and clinical notes into structured digital text for NHS systems.
Extract claim details, policy numbers, and supporting evidence from scanned claim documents and photographs.
Process research papers, extract citations, tables, figures, and structured data from complex academic layouts.
Digitise and extract data from government forms, applications, and correspondence at scale.
Interpret blueprints, technical drawings, and architectural plans. Extract annotations, dimensions, and labels.
Convert handwritten notes, letters, and annotations into searchable, editable digital text using vision AI.
Integrate Cyclops into your existing workflows in minutes.
curl -X POST https://api.hush-ai.uk/v1/cyclops/process \ -H "Authorization: Bearer YOUR_TOKEN" \ -F "[email protected]" \ -F "mode=ocr" # Response { "text": "extracted content...", "mode": "ocr", "filename": "invoice.pdf", "file_type": "application/pdf", "chars": 4820 }
curl -X POST https://api.hush-ai.uk/v1/cyclops/process \ -H "Authorization: Bearer YOUR_TOKEN" \ -F "[email protected]" \ -F "mode=eye"
Every layer hardened. Every request audited.
Every request authenticated with scoped bearer tokens. No anonymous access.
Strict path validation prevents directory traversal and unauthorised file access.
Per-token rate limiting prevents abuse and ensures fair resource allocation.
Every document processed is logged with timestamp, token, and metadata. Exportable.
Documents processed on hardware we physically own in the United Kingdom.
Data controller C1912355. UK GDPR compliant. DPIA available on request.