The real catalog of tools for AI agents

Vision tools for coding agents: screenshots, OCR, UI diffs, errors, tables, and charts.

MCP server for browser and desktop automation: OCR, image recognition, real mouse and keyboard input

Image/video analysis: NSFW detection, object detection, thumbnails

Real-time screen capture + AI vision for Claude — see, analyze, and OCR your screen

ROC biometrics & computer vision: face, LPR, OCR, pedestrian, vehicle, gun detection.

Analyze images from multiple angles to extract detailed insights or quick summaries. Describe visu…

Real-time physical perception for AI agents — vision, spatial, acoustic, environmental

Local visual UI cache for AI agents using perceptual hashing, CLIP, and 3D spatial grounding.

Local OCR & screen understanding for agents: read any window, find what to click. No uploads.

Visual Intelligence Command Center: A Local Computer Vision Engine for Photo Libraries

Generate and edit AI images, video, voice and music, and render motion graphics with Splice.

Image understanding for AI agents — analyze and describe any image via the three.ws pipeline.

Multimodal video analysis MCP — transcription, vision, and OCR for any video URL.

Easy and stylish presentation slide generator.

C2PA standard visual authenticity scanner and metadata auditor.

Shrink images to a token budget for vision LLM agents and pipelines. Not for chat-pasted images.

Computer use for Hyprland: semantic desktop state over IPC, plus vision and native input

PDF reader for vision LLMs. Auto-detects text corruption and switches to image mode.

Check work from photos: read results, write checks in plain words, send photos for a verdict.

Read-only machine-vision calculations for optics, interfaces, line scan, sensors, and models.