Skip to content

Latest commit

 

History

12 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 

Repository files navigation

dLLM Lens

A browser extension that uses diffusion LLMs to help you navigate and simplify any webpage in real-time.

Why diffusion LLMs?

Traditional LLMs generate tokens one at a time. Diffusion LLMs generate tokens in parallel — refining the entire response at once. At 150ms response times and 2000+ tokens/second, UI interaction feels instant. And it's getting faster every quarter.

This extension explores what becomes possible when language models are fast enough for real-time UI manipulation.

Install

  1. Clone the repo: git clone https://github.com/your-username/dllm-lens.git
  2. Open chrome://extensions and enable Developer mode
  3. Click "Load unpacked" and select the extension/ folder
  4. Click the extension icon and paste your API key

Supported Models

Model Provider Speed Default
Mercury Coder Inception Labs ~2000 tok/s Yes
Celeris-1 Celeris AI ~2000 tok/s
Any OpenAI-compatible Various Varies

BYOK — bring your own key. The extension calls the model API directly from your browser. No backend server, no data collection.

Want to add a model? See Adding a Model Profile.

How It Works

Guide mode — Ask where something is on the page. The extension analyzes the DOM, finds the element, and highlights it with an overlay.

"Where do I change my shipping address?"

Simplify mode — Tell it something is confusing. It rewrites the DOM region to be clearer, preserving functionality. Fully reversible.

"Simplify this checkout form"

Under the hood: the extension prunes the page DOM (strips scripts, styles, hidden elements, collapses wrapper divs), sends it to a diffusion LLM with your request, and applies the structured response — either as a visual overlay or a DOM rewrite.

Limitations

  • Large or deeply nested pages may hit model context limits
  • Rewrites are cosmetic — they don't persist across page loads
  • Complex SPAs with heavy client-side rendering may produce stale DOM snapshots
  • No vision input yet (DOM text only) — accuracy depends on DOM quality
  • Some sites with strict Content Security Policies may block the widget injection

Future

  • Vision input — send screenshots alongside DOM for better element identification
  • Streaming rewrites — progressive DOM updates as the model generates
  • Automatic improvements — learn from user interactions to suggest fixes proactively
  • Site-owner embed mode — drop a script tag to improve your site's UX for all visitors

Contributing

The most useful contributions right now:

  1. Try it on unusual sites and file issues when it breaks
  2. Add model profiles for new diffusion LLMs as they launch
  3. Improve DOM pruning — better heuristics for what to keep and what to strip

License

MIT

About

Browser extension using diffusion LLMs for real-time webpage navigation and simplification

Topics

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages