Menu
Theme

Years I contributed:2025–2026AI · Developer tools · Open source

Browser AI

Framework APIs and components for Chrome’s built-in AI, created after working through undocumented LanguageModel API behavior.

My role
Creator & key maintainer
Context
Personal initiative · DeSource Labs · Open source
Explore the project

I wanted to use the new LanguageModel API and ran into challenges and undocumented behavior. I started writing wrappers, helpers, and fixes around the integration. Those pieces grew into Browser AI, which I created and continue to maintain.

The library brings local AI capabilities into Vue, Nuxt, React, Angular, Svelte, and plain TypeScript. It provides framework-native components and headless APIs for chat, writing, translation, and related browser capabilities.

Built with
TypeScriptVue / NuxtReactAngularSvelteChrome built-in AIWebMCP
  • Model readiness and request controls

    Built availability checks, download-progress state, streaming responses, and cancellation into reusable APIs around the browser’s built-in models.

  • Framework-native integration

    Provided a shared core with Vue composables, React hooks, Angular signals and services, Svelte stores, and client-safe Nuxt integration.

  • A family of browser AI tools

    Built interfaces for summarization, rewriting, translation, proofreading, and language detection, alongside chat and WebMCP tooling.

Restoring a conversation within the model’s limits

A saved conversation can outgrow the model’s context window. Reloading the transcript into a new session therefore needs a decision about which messages fit and how much earlier context to retain.

I implemented restoration that measures the conversation against a configurable context budget. It can keep recent messages or summarize older exchanges, and it can reuse cached summaries when restoring the same history again.

Summarization can fail or take too long, so the implementation includes time limits and a fallback to recent messages. It also exposes restoration progress and whether only part of the conversation was loaded, giving the application enough information to explain the session’s state.

My independent practice

My independent work spans client collaborations and my own developer tools. I established my business in January 2025, building on earlier project work. I handle architecture, implementation, and delivery; when a project needs more capacity, I can bring designers and engineers through DeSource Labs.

Career timeline January 2025–present

  1. Individual Entrepreneur / Software Development Consultant

    January 2025–present

Broader responsibilities

Hands-on product development and technical consulting through my own business.

  • Develop web applications, front-end systems, and integrations for clients, from technical planning through implementation and handover.
  • Work on software architecture, backend and infrastructure planning, AI integrations, and blockchain applications.
  • Create and maintain developer tools including Phone Mask, DeSource Image, Context7 Widget, and Browser AI.
Full CV
Start a conversation

What are you
working on?

An engineering role, a product to build, or a technical problem to work through. I’d like to hear about it.