AI Demos at the Edge

These demos showcase Workers AI running at 300+ global locations with sub-50ms response times.
Real AI applications solving real problems at the speed of light.

⚠️
Public Beta Build

Some demos are still being perfected. If something breaks, congratulations—you found a feature request.

More demos are in active development. Check back soon or follow the Projects page for updates.

🚫 For Those Who Hate BS

🏴‍☠️

The Anti-Portfolio

Tired of "revolutionary AI-powered solutions"? Visit my BS-free zone with the AI Strategy Diagnostic, Hype Graveyard, and VC Mad Libs generator.

Enter BS-Free Zone

Under the Hood

Models Used

  • @cf/meta/llama-3.1-8b-instruct - Chat & Analysis
  • @cf/baai/bge-large-en-v1.5 - Embeddings

Performance

  • Global deployment in 300+ locations
  • Cold start latency: < 1ms
  • Avg response time: ~25ms
  • Cost per request: $0.000001

Architecture

  • Astro SSR on Workers
  • Streaming responses via SSE
  • D1 for persistence
  • R2 for asset storage