The archive your institution deserves — cataloged by AI, curated by you.
Archively.AI is a modern, multi-tenant platform for libraries, universities, and government archives. Upload anything, let AI draft the description, and publish to international standards — without leaving your workflow.
- 7
- Catalog modules
- 4
- Standards
- 30+
- File types
A working surface built around the catalog record.
Not a wiki, not a spreadsheet. Every item is a live document with AI-drafted fields on one side, the source on the other, and a persistent track-changes bar so nothing ships without curator sign-off.
- AI badge shows which fields were drafted by the model
- Scope & content, creator, dates, and subjects shown inline
- Save / revert bar tracks unsaved edits across tabs
- One-click publish locks an immutable snapshot
Everything an institutional archive needs, in one place.
Archively.AI replaces a stack of legacy tools: DAMs, cataloging software, OCR services, and finding-aid publishers. One platform, one standards-compliant data model.
AI-assisted description
OCR, transcription, entity extraction, and summaries turn uploads into review-ready metadata in minutes — with every suggestion track-changed.
Standards-first
ISAD(G), Dublin Core, MARC21, PREMIS — mapped, not bolted on.
Multi-tenant
Many institutions, one deployment. Isolated storage, auth, and policies per tenant.
Every file type
Images, PDFs, audio, video, spreadsheets, Office — the right viewer and pipeline for each.
Talk to your archive
RAG chat grounded in your holdings. Every answer cites the item, page, or timestamp.
Track changes everywhere
Three layers — AI draft, curator review, immutable publish — with inline diffs and one-click revert.
Live usage, soft landings
Per-tenant metering with 80/95/100% thresholds. Hard limits become friendly upgrade modals — never dead-end errors.
Image editor in-product
Crop to archival presets, deskew, AI object detection, archival captions — without leaving the file detail.
Stories — a blog for the catalog
Notion-style block editor with entity-aware cards. Drop in items, people, or a four-column gallery, then publish to your portal.
A public portal per tenant
Branded subdomain, six visual templates, four asset slots, four feature flags — flipped without a deployment.
From upload to published finding aid.
Search any entity, let AI fill in the fields, review every change with full diffs, and publish a citable, immutable record — in one continuous workflow.
Watch a record move through the pipeline.
Upload, AI describe, review with diffs, publish. Four stages, one audit trail. This demo cycles the states; you can tap a stage to jump.
AI drafts. Curators decide. Every edit, remembered.
Three layers — AI output, curator review, and the immutable published snapshot — sit side by side. Inline diffs show exactly what changed; one click reverts or publishes.
An immutable snapshot of what the model produced.
Your working copy, with pristine/dirty tracking.
Signed, dated, and locked. Citable for decades.
Seven modules, one coherent model.
Every entity is tenant-scoped, track-changes enabled, and server-searchable with facets.
Items
ISAD(G)-shaped records.
Fonds
Hierarchical arrangement.
People
Creator authorities.
Organizations
Corporate bodies.
Accessions
Acquisition tracking.
Subjects
Topical access.
Events
Contextual timelines.
More modules on the roadmap: exhibitions, requests, and reading-room workflow.
See all features →One platform. Four very different institutions.
The data model is the same. The workflows and portals adapt to how your institution actually works.
The work the ILS wasn't built for.
Public, academic, and specialist libraries catalog special collections, publish finding aids, and sync with their existing ILS — without forcing manuscripts into bibliographic records.
Explore solution →- MARC21 authority sync with your ILS
- EAD export for finding aids
- Patron portal per collection
Four live tenants. One deployment.
We run four fictional institutions on the same platform so you can explore what a real deployment feels like — without signing up for a trial.
Northbridge Medical Society Papers
1891 – 1935
Manuscript archive of a fictional provincial medical society, including 1918 pandemic correspondence.
See it →Ridgewood College Oral History Project
1975 – 2015
Audio and video interviews with alumni, faculty, and townspeople — one under embargo.
See it →State Records of Thornwood
1918 – 1925
Public-health records with chain-of-custody, redaction, and PREMIS preservation metadata.
See it →Harbor Museum Archives
1961 – present
Exhibition records, donor histories, and curatorial research files with events as first-class records.
See it →What archivists tell us.
From archivists, records managers, and curators — the people who use this every day.
“We replaced a spreadsheet, a home-grown PHP catalog, and a paid OCR service with one product. The finding aids look better than what we had in print.”
Ready to retire your legacy cataloging stack?
Spin up a tenant, import a small collection, and see a standards-compliant, AI-described finding aid in an afternoon.