video-db/videodb-capture-quickstart
Give your agents real time desktop perception. Stream screen, microphone, and system audio for live context and actions.
Provides token-based architecture that keeps API keys server-side while streaming desktop media through client tokens, with webhooks and WebSocket channels delivering structured AI outputs (transcripts, visual/audio indexes) in real-time. Supports both Node.js and Python SDKs, integrating with agentic frameworks like Claude Code and Cursor through a flexible RTStream pipeline model where you control which AI processors run on captured channels.
Stars
23
Forks
4
Language
Python
License
ISC
Category
Last pushed
Mar 12, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/video-db/videodb-capture-quickstart"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
GetStream/Vision-Agents
Open Vision Agents by Stream. Build Vision Agents quickly with any model or video provider. Uses...
TheSethRose/AI-File-Organizer-Agent
Uses an AI agent (powered by Google Gemini via the Agno framework) to intelligently propose and...
Karmacoke/chargen
AI-powered character generator built with React. Create detailed TRPG/Novel characters, NPC...
grctest/g3n-fastapi-webcam-docker
Utilizing multiple Gemma 3n agents to analyze webcam footage
leukaemiamedtech/hias-tassai-facial-recognition
HIAS TassAI Facial Recognition Agent processes streams from local or remote cameras to identify...