10 actions in 6 pieces of software · ranked by words, meaning and measured trust · 653 ms

1. 1UI-Venus-2-9Bverified and signedpassport

   modelrecord15,463 downloads/month

   • image-text-to-text

     Task: image-text-to-text

2. 2UI-Venus-2-9B GUI Groundingdemo or tutorialno passport yet

   MCP serverrecord

   • ui_venus_2_9b_demo_predict

     Predict the click coordinate for a target element on a GUI screenshot. Given a screenshot and a natural-language description of the element to locate, UI-Venus-2-9B predicts the center-point coordinates in normalized [0, 1000] space and marks it on the image. If a user passes a file as an input, use

3. 3gemma-2-9bverified and signedpassport

   modelrecord36,863 downloads/month

   • text-generation

     Task: text-generation

4. 4google-deepmind/gemma2-9b-itverified and signedpassport

   modelrecord

   • google-deepmind/gemma2-9b-it

     Google's Gemma2 9b instruct model

5. 5UI-Venus MCPfound in code, not yet checkedno passport yet
   • computer_screenshot

     Capture the screen/window/display. Returns metadata + image content; optionally saves to a file.

   • computer_get_state

     Cheap structural state: screen info, frontmost app, windows, capabilities. No screenshot.

   • computer_locate

     Find an element by natural language or structured descriptor. Structured (UIA/AX/AT-SPI/DOM) first, UI-Venus vision grounding as fallback; vision points are snapped back to structured elements when possible. Coordinates in results are screenshot pixel space; use with computer_action.

   • computer_verify

     Verify a goal against the current screen: structured UI-tree heuristics first, UI-Venus vision verification as fallback. Supports structured assertions (checked/exists/value/textVisible).

   • computer_record_stop

     Stop recording and return the recorded entries.

6. 6black-forest-labs/flux-2-klein-9bverified and signedpassport

   modelrecord

   • black-forest-labs/flux-2-klein-9b

     4 step distilled version of FLUX.2 [klein]. A foundation model for maximum flexibility and control