your agent is blind (hermes, openclaw or any other ai agent you are using)
mine reads screenshots, diagrams, UI mockups, whiteboards, error logs from photos - everything
nvidia nemotron 120B vision model
free on openrouter right now, no card, no waitlist
what it sees:
- UI screenshots
- handwritten notes
- charts and diagrams
- error logs from photos
- code screenshots
- product mockups
you can run it in:
hermes agent (easiest, full setup below)
openrouter API directly
any openai-compatible client
HERMES AGENT SETUP (free, 5 min):
> go to https://t.co/F33CTVpWY6 and create an account
> click "Models" in the left sidebar
> click "Add Custom Model"
> in the provider dropdown select "OpenRouter"
> paste your OpenRouter API key (free at https://t.co/T65Fsizl9T)
in the model ID field paste exactly: nvidia/nemotron-3-super-120b-a12b:free
> set context window to 131072
> enable "Vision" toggle
> click Save
open any new chat, select the model from the dropdown
drag and drop any image into the chat
it will describe, analyze, and reason over everything it sees
no subscription. $0. works today.
save this and gave your agent a vision