MemoRay Founder Access for Windows 0.3.0

Import review and processing

• Selecting files or a folder now adds files to an explicit review list before processing begins.
• Active processing shows completed/total progress and the current filename when available.
• Indexing reuses text already produced during import instead of running duplicate OCR.

Answers and source review

• Ask MemoRay continues to show supporting sources.
• Cited sources open at the available page or location for comparison with the original document.
• ID, card, passport, and similar OCR-derived details use safer review wording and remain marked for review.

Supported file types

Supported now: PDF, DOCX, JPG, JPEG, PNG.

MemoRay Founder Access for Windows supports PDF, DOCX, JPG, JPEG, and PNG. Unsupported file types are skipped during Import review and do not block supported files in the same selection.

Trust and privacy boundaries

Core processing, indexing, search preparation, and Ask MemoRay work on selected or imported documents locally on the device. The core workflow does not require document upload.

Network access is used for Founder Access license activation and validation, update checks, and optional support pages or forms the user opens.

Protected documents

• Protected documents use a password created locally inside MemoRay. Founder Access license keys are for activation only. RayAI/MemoRay cannot recover that password; if it is forgotten, remove the current MemoRay workspace and import documents again before setting a new password. Original files outside MemoRay are not deleted.
• Remember and retain the password before updating.
• Do not uninstall with data removal or manually delete the local MemoRay workspace during an update.

Founder Access validation and support

• Founder Access validation uses the production-equivalent Founder/Tesseract configuration.
• Support entry points can prefill the contact email when available.
• Support links do not automatically attach document content, license keys, passwords, or local diagnostic files.

Founder Access OCR boundary

• Founder Access uses the production Tesseract/PDFium OCR and text-extraction path.
• The experimental Worldclass OCR option is not included in Founder Access.
• Text-based and scanned/image-based PDFs are supported; scanned PDFs and images use on-device text reading.
• Readable, unencrypted DOCX files are supported. Encrypted or malformed DOCX files are rejected.

Known limitations

• MemoRay includes local text reading for scanned PDFs and images. Standard documents usually work best. Some low-quality scans, rotated cards, IDs, passports, membership cards, business cards, and handwriting-heavy images may be classified less precisely or may miss structured details. Review the source document when accuracy matters.
• Difficult scans, low-quality images, IDs/cards, complex layouts, and OCR-derived details may require review.
• OCR-heavy files may process more slowly, especially on weaker consumer machines.
• Multi-column manuals and PDFs can have imperfect reading order or interleaved text.
• Search is limited to text MemoRay successfully extracts and indexes.
• Successful import does not guarantee that every word or structured detail is searchable.
• Compare generated details and answer evidence with the source preview before using them for important decisions.