Skip to main content

View All Examples on GitHub

Complete source code and installation guides

​
AI Copilots

Give your AI agents eyes and ears. Build assistants that see what users see and hear what they hear - in real-time.

​
When to Use This

  • You’re building a coding assistant that understands the user’s screen
  • You want an AI sales coach that listens to calls in real-time
  • You need a productivity tracker that knows what app you’re in
  • You’re creating any AI agent that needs visual/audio context

​
What You’ll Build

Pair Programmer

AI coding assistant with real-time screen and audio context

Sales Copilot

Real-time coaching during sales calls with cue cards

FocusD

Productivity tracking with automatic session summaries

CRM Sales Agent

Director-powered agent for sales automation

​
Architecture: Two-Runtime Design

Capture SDK Architecture showing two-runtime design with backend API key and desktop client token Why? API keys never touch the desktop. Tokens are short-lived. Enterprise-ready security.

​
How It Works

Backend creates session → Generate client token → Desktop captures → AI processes → Agent responds

Capture SDK Overview

Full architecture and capabilities

Real-Time Context

How real-time AI context works

Privacy Controls

User consent and data protection

Storage & Search

Persist and search captured content

MCP Server

Connect VideoDB to Claude and other agents

Director Framework

Build custom AI agents with VideoDB