From records to family trees
Machine learning that reads any historical record — handwritten documents, journals, parish books, civil registers — extracts names, dates, and relationships, and builds genealogical trees automatically.
Request AccessExplore a living family tree
Drag, hover, and zoom through a sample family spanning five generations. This is a taste of what GlyphForge builds automatically.
GPU-accelerated rendering is not available. Please enable hardware acceleration in your browser settings to use the interactive graph.
How to enable: Go to your browser settings and search for "hardware acceleration" or "GPU rendering", then enable it and restart your browser.
Export your data directly to GEDCOM — compatible with FamilySearch, Ancestry, MyHeritage, and more.
Capabilities
An end-to-end ML pipeline that turns scanned records into structured, queryable family trees.
Relationship Extraction
Detects parent-child, spouse, godparent, and sibling relationships from contextual clues in historical records.
Handwriting Transcription
Purpose-built models that read centuries-old cursive, fraktur, and degraded manuscripts with high accuracy.
OCR & Document Intelligence
Robust optical character recognition for printed and handwritten text across parish registers, civil records, and censuses.
Data Extraction
Automatically identifies and structures names, dates, places, and life events from unstructured document text.
Records to Trees
Connects extracted individuals across thousands of pages into validated, deduplicated family trees ready for research.
Automated Validation
Over 30 integrity checks catch impossible dates, duplicate entries, and structural errors before they reach your tree.
How it works
Four steps from scanned page to searchable family tree.
Upload
Scanned parish records, civil registers, or family books in PDF format.
Extract
HTR and NLP models read handwriting and identify people, dates, and relationships.
Build Graph
Extracted data is ingested into Neo4j and validated with 30+ integrity checks.
Explore
Visualize the family tree in an interactive force-directed graph at 60fps.