DEV Community: ALAN S

WebChange — Let AI Watch Websites for You

ALAN S — Sun, 25 Oct 2026 18:45:16 +0000

🦥 WebChange — Let AI Watch Websites for You

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady.

What I Built

I built WebChange, an AI-powered website monitor that automatically checks websites and helps identify important updates.

Instead of repeatedly refreshing websites, WebChange does the work for you!

Features:

🔍 Automatic website monitoring
🧠 AI-generated change summaries
🔔 Important and minor change detection
📊 Simple dashboard
🕒 Automatic checks every 6 hours
📜 Change history

Demo

🌐 Live Demo: https://webchange.e1ite.workers.dev

WebChange lets you add websites, monitor changes, and see AI-generated explanations in one dashboard.

The app runs on Cloudflare without needing a VPS or an always-on computer.

Code

💻 GitHub: Repository publication pending.

How I Built It

I used Cloudflare Workers, D1, Cron Triggers, and Workers AI with the open-weight Qwen model.

Cloudflare Workers handles website monitoring.
D1 stores website snapshots and change history.
Cron Triggers runs checks automatically.
Workers AI analyzes changes and generates summaries.

The entire application uses a serverless architecture.

Why Does Open Innovation Matter?

Open-weight AI allows developers to customize how changes are analyzed and experiment with different models.

It also reduces dependence on proprietary AI APIs.

Combined with Cloudflare's serverless infrastructure, WebChange is designed to run at a low cost without maintaining a dedicated server.

The Lazy Payoff

Instead of checking multiple websites every day, I can add them to WebChange and let AI do the repetitive work.

Less refreshing. Fewer distractions. More free time. 🦥

That's what Slow and Steady means to me!

ArchiveRescue — Restore Old Documents with Open-Source AI

ALAN S — Mon, 19 Oct 2026 04:29:22 +0000

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle

What I Built

I built ArchiveRescue, a tool that helps restore and digitize old scanned documents using open-source AI.

Users can upload documents, improve image quality, extract text using OCR, and download the results.

Features include:

Image enhancement and noise reduction.
OCR text extraction.
Selecting specific areas for OCR.
Editable transcription.
Confidence warnings for inaccurate results.
Exporting documents and text as ZIP files.

This could be useful for historians, researchers, museums, and freelancers offering document digitization services.

Demo

Live Demo: https://archiverescue.e1ite.workers.dev/

Upload a document, choose an enhancement mode, and click Restore & transcribe.

You can review the extracted text, make corrections, and download the results.

Code

GitHub: https://github.com/shadowe1ite/ArchiveRescue

The project is open-source under the MIT license.

How I Built It

I used several open-source tools:

Tesseract.js — OCR directly in the browser.
OpenCV — Image enhancement and noise reduction in the Python version.
TrOCR — Experimental handwriting recognition using an open-weight model in the local version.
Gradio — Interface for the Python version.
Cloudflare Workers — Hosting the browser demo.

One challenge was recognizing handwritten documents. The initial OCR results weren't accurate, so I added region selection, image enlargement, and confidence warnings.

Handwriting recognition still needs improvement.

Why Does Open Innovation Matter?

I chose open-source AI because it allows documents to be processed locally without uploading them to third-party OCR services.

It also keeps costs low since there are no per-document API charges.

Using open-source tools gives me the freedom to improve the OCR pipeline, experiment with different models, and add new features without depending on proprietary services.

My Agent Session

I used AI coding assistance to help build and improve the project. I haven't recorded a DevRelay session.

My First User

I tested the application with a historical document. The OCR struggled with handwritten text, which helped me identify areas to improve.

I haven't had a paying user yet.

Prize Categories

Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle.

Demo: https://archiverescue.e1ite.workers.dev/

Source Code: https://github.com/shadowe1ite/ArchiveRescue

Thanks for checking it out!

BirdEcho: Discover Birds Around You with Open-Source AI 🐦

ALAN S — Sun, 11 Oct 2026 19:55:05 +0000

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass.

What I Built

I built BirdEcho, an AI-powered bird sound identification app that encourages people to step outside and explore nature.

Ever heard a bird singing and wondered what species it was? With BirdEcho, you can record its sound and let AI identify it.

The app also lets you:

🎙️ Record or upload bird sounds.
🐦 Identify birds using AI.
📖 Save discoveries in a personal bird journal.
🌿 Learn about different bird species.
🔒 Analyze recordings privately on your device.

The goal is simple: less scrolling, more exploring!

Demo

🌐 Live App: https://birdecho.pages.dev

Open the app, record a bird singing, or use the built-in sample to try bird identification.

Code

💻 GitHub: https://github.com/shadowe1ite/birdecho

The complete source code is publicly available, including setup instructions and model documentation.

How I Built It

I built BirdEcho using React, Vite, BirdNET+, and ONNX Runtime Web.

BirdEcho uses the BirdNET+ V3.0 model to recognize bird sounds. Audio is processed directly in the browser using WebAssembly, without sending recordings to an AI server.

The app uses:

BirdNET+ for bird sound identification.
ONNX Runtime Web for local AI inference.
React and Vite for the interface.
IndexedDB to save recordings and discoveries.
Cloudflare Pages for hosting.

One challenge was running a large AI model inside the browser while keeping the app responsive. I used Web Workers to handle inference and split the model into smaller downloadable chunks.

Why Does Open Innovation Matter?

Openly available AI models made BirdEcho possible without depending on paid AI APIs.

By running AI locally, BirdEcho can identify birds without uploading their recordings to external inference services.

The application's code is open source under MIT, while the BirdNET+ model has its own CC BY-SA 4.0 license and additional usage restrictions.

I believe AI shouldn't always keep us glued to screens. Sometimes, it should encourage us to explore the world around us.

That's the idea behind BirdEcho. 🌿🐦