RYAN ZERNACH

Senior AI Systems Engineer

Ryan_Zernach_2025_Senior_AI_Systems_Engineer_Remote_United_States

💬 Chromium History Chat

Chrome extension that turns browsing history into a conversational, AI-powered memory layer. Ask natural-language questions about pages you already visited, recover research trails by fuzzy memory instead of exact keywords, and revisit prior work through a privacy-aware stack that combines on-device Rust/WebAssembly processing with a serverless Go backend.

Related Links
Chrome Web Store
GitHub Repository
Privacy Policy
💬 Chromium History Chat

Chromium History Chat walkthrough

Summary

Chromium History Chat is a Manifest V3 Chrome extension that lets you ask natural-language questions about pages you have already visited. History is processed client-side with Rust compiled to WebAssembly, then paired with a Google Cloud Function written in Go that handles OpenAI requests, rate limiting, and credential management so users can query their browsing history without having to manage backend infrastructure themselves.

Tech Stack

Chrome Extension (Manifest V3), Rust to WebAssembly, Dart compiled to JavaScript for UI and service worker, Go (Google Cloud Functions Gen 2), Google Secret Manager, OpenAI GPT-4o-mini, HTTPS-only transport.

Distribution

Published on the Chrome Web Store with a public GitHub repository, a dedicated privacy policy route, and a portfolio post that documents both the product story and the architecture behind it.

Key Details

The sections below cover Product, Client architecture, and Backend + AI.

Product

Client architecture

Backend + AI

What this extension does

Chromium History Chat lets you have a real conversation with your browsing history. Instead of trying to remember the right keyword, digging through hundreds of old tabs, or scrolling endlessly through the default history page, you can ask a question in plain English and get a helpful answer backed by the pages you actually visited. You do not have to remember exact URLs, page titles, or search queries. If you can describe what you were doing or what you remember from the page, Chromium History Chat can help you find it again.

What you can do with it

Turn browser history into something you can query, summarize, and revisit.

Example prompts

The kinds of questions the product is designed to answer.

How it works in practice

No special syntax, no query language, no keyword roulette.

Why you might want this

The default History view treats your prior browsing as a simple timestamped list. Chromium History Chat upgrades that into something closer to a searchable, conversational memory, so instead of thinking "I know I saw this somewhere..." you can think "past me already researched this; let me ask what I found."

Turn your browsing history into a personal knowledge base

Save time every single day

Perfect for research-heavy work

Learn and review more effectively

Find things by fuzzy memory, not exact text

Why it needs access to your browsing history

This extension is specifically designed to work with your browsing history, so it needs permission to read history entries. Without that access, there is nothing to chat with. The permission exists so the product can understand which pages you visited, organize them into a reusable index, and answer questions grounded in your own browsing rather than generic web search.

History permissions in practice

Who this extension is for

Why install it now

In short

Project overview

This project demonstrates a full vertical slice: browser-native UX, semantic recall over real user history, WASM performance on-device, and a production-shaped serverless backend with rate limits and secret management. It is a practical answer to "I know I saw this somewhere" without asking users to change how they browse.

Why this stands out

Shipping a Chrome Web Store extension with Rust/WASM, a Go Cloud Function, and a clear privacy story shows end-to-end ownership across client performance, cloud operations, and AI product design. It is not a single-stack toy demo; it is a product-shaped implementation with an actual distribution channel, explicit permissions narrative, and a real user workflow.