An open-source experiment · Public-domain sourcing
Context-aware image sourcing
for the Public Domain.
Stop generating. Start discovering.
In an era of AI-hallucinated imagery, OpenVisualist prioritizes the provenance of the real. It reads a draft, understands what it's actually about, and sources genuine public-domain photography to match — for writers, historians and publishers who'd rather cite a source than fabricate one.
- 01Contextual analysis
- 02Visual query expansion
- 03Archive sourcing
2 ways to see it live
This is a real interface, not a screenshot — but it needs its own engine running somewhere. Pick one:
01
Via Terminal
Run the API on your own machine and point this page at it.
- Clone the repository.
pip install -r requirements.txtuvicorn api.main:app --reload --port 8000- Leave the API URL field below on
http://localhost:8000.
02
Use Render
Deploy a public copy of the API from your browser — no terminal, no API key required.
- Deploy to Render, sign in, click Apply.
- Copy the service URL Render gives you once it's live.
- Paste it into the API URL field below.
Try it
Talks directly to POST /analyze-and-source — nothing here is simulated. No API pointed at it yet? Typing below will just show a connection error, that's expected, not broken.
Start writing — suggestions appear after a pause