DEV Community: Satwik Pagi

Susegad Desk: Private, Guest Check-In for Small Homestays

Satwik Pagi — Mon, 19 Oct 2026 08:19:15 +0000

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

What I Built

Susegad Desk is a privacy-first guest check-in tool for small homestays and guesthouses.

When a guest arrives, the owner can take a photo of an ID using a phone on the homestay’s local Wi-Fi. The local app runs the image through Tesseract OCR, then uses Phi-3 Mini through Ollama to turn the recognized text into structured guest details. The owner reviews and edits those suggestions before adding them to a register.

The goal is to replace repetitive manual transcription with a quicker workflow that can run on the homestay’s own computer. It’s designed for small operators who want to avoid per-request AI costs and keep the ID-processing workflow local.

Demo

susegad-desk3.vercel.app

Code

satwikpagi5-wq / susegad_desk3

Privacy-first guest check-in demo for local homestays. Includes a Vercel static demo and a local OCR app.

Susegad Desk

A privacy-first guest check-in prototype for independent homestays. Susegad Desk turns an ID photo into editable guest details using OCR and a local language model, then requires human review before adding anything to the day register.

Prototype and privacy notice: The Vercel version is a fictional-data demo only. It does not accept ID images and does not connect to the OCR service. The full OCR workflow runs on a reception computer on a trusted local network. This is not a legal or compliance product.

Hosted demo

The static Vercel build is served from web/. It demonstrates the review form, session-only guest register, and CSV export with fictional values. It intentionally has no upload field: government ID images must not be sent to this public demo.

Local app

The full local app is served by FastAPI from server.py, with its UI in static/. Images are processed…

View on GitHub

How I Built It

The project has two parts:

A local FastAPI backend that receives an ID image, runs Tesseract OCR, and sends the extracted text to Ollama on the same computer.
A responsive web interface for reviewing the extracted fields and maintaining a session-only guest register. The stack is Python and FastAPI for the backend, Tesseract for OCR, Ollama for local model inference, and HTML, CSS, and JavaScript for the interface. The hosted demo is a separate static site, so it can show the workflow without handling identity documents. The extraction is treated as a suggestion, not a final record: the owner must review the fields before adding them.

Why Does Open Innovation Matter?

Local inference is central to this product. A cloud OCR or AI API would require internet access during processing, introduce recurring usage costs, and send sensitive identity data to a third-party service.
With Phi-3 Mini running locally through Ollama, the homestay can process documents on its own computer without a per-request model bill. Once the model and dependencies are installed, the check-in workflow can continue during an internet outage, as long as the computer and local network remain available.

That makes a one-time installation model more plausible for small homestays than a monthly subscription. It also lets the operator keep the document-processing workflow on hardware they control. This prototype is not a compliance product, and every extracted field still needs to be checked against the source document.

Prize Categories

None. The project does not currently use any of the listed partner technologies in a way that qualifies for a partner category.

AvianEcho: The Open-Source Wildlife Listener

Satwik Pagi — Fri, 09 Oct 2026 14:07:24 +0000

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

What I Built

AvianEcho is an offline-capable, Edge AI bird identification dashboard designed to run entirely on local hardware. The application captures real-time environmental audio or processes uploaded sound files, standardizes the audio frequencies, and classifies the exact bird species using an optimized ONNX BirdNET model.

To create a complete field guide experience, it dynamically fetches verified wildlife photography from the Wikipedia REST API, generates fascinating context and lore using a locally hosted Gemma LLM, and reads those facts aloud using the Piper text-to-speech engine.

Demo

drive.google.com

Code

satwikpagi5-wq / avian_echo

🐦 AvianEcho — Real-Time Edge AI Bird Guide

Listen to Nature. Discover the Birds Around You.

An AI-powered bird identification and discovery platform combining real-time audio analysis, edge machine learning, local language models, and voice-based storytelling

🧭 Explore AvianEcho

📖 About the Project

AvianEcho is an AI-powered bird identification and exploration application that helps users discover bird species through their vocalizations.

Bird calls are one of nature's most useful identification signals, but recognizing them can be challenging without specialized knowledge. AvianEcho makes this process more accessible by combining audio classification, locally running AI models, educational content generation, and natural-sounding voice feedback.

The application analyzes live microphone input or uploaded audio recordings, identifies likely bird species through a BirdNET-based classification pipeline, and presents the results through an interactive Streamlit dashboard.

It can also generate engaging bird facts using a locally hosted Gemma 2B language model and read those facts aloud using…

View on GitHub

How I Built It

I built the frontend using Streamlit to create a clean, dual-tab interface for both file uploads and live microphone scanning. The core backend relies on Python, utilizing librosa and numpy to manipulate audio chunks into the exact 48kHz, 3-second mono format required by the classification model.

To keep this a true Edge AI prototype that can run offline in the wilderness, I avoided cloud APIs for the heavy lifting. I implemented llama-cpp-python to run a local Gemma 2B model for generating educational bird facts, and piped that text into a standalone Piper TTS Windows executable for instant voice synthesis. The only external call is to the Wikipedia REST API to ensure the photographs displayed are biologically accurate rather than AI-generated hallucinations.

Why Does Open Innovation Matter?

Open innovation democratizes access to advanced technology. By leveraging open-source models, lightweight TTS engines, and open knowledge bases like Wikipedia, a student can build a sophisticated environmental monitoring tool without requiring massive cloud computing budgets or proprietary APIs. In the context of wildlife conservation, open innovation ensures that tools like AvianEcho can be freely modified, deployed on low-cost hardware like Raspberry Pis, and utilized in remote habitats where internet access doesn't exist.

Prize Categories

Best use of Gemma

Campus care : A real time issue tracker for University life.

Satwik Pagi — Sat, 03 Oct 2026 18:55:56 +0000

This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend

What I Built

I built Campus Care, a transparent, real-time issue-tracking and resolution platform designed to bridge the gap between students and maintenance staff at my University.

The Problem:
On a busy campus, issues like broken projectors, flickering library lights, and plumbing problems can easily go unnoticed or get buried in endless WhatsApp groups. Students often have no way to know whether their complaints have been received or addressed, while maintenance staff lack a centralized system to organize tasks, track progress, and showcase the work they complete.

Campus Care aims to make reporting, tracking, and resolving campus issues simpler, faster, and more transparent for everyone.

Demo

campus-issue-tracker-eight.vercel.app

Code

satwikpagi5-wq / campus-issue-tracker

🏫 Campus Care

Report • Resolve • A Better Campus

A transparent, real-time campus issue tracking and resolution platform built for students and maintenance staff

About • Features • Tech Stack • Structure

📌 About the Project

Campus Care is a transparent, real-time issue-tracking platform designed to simplify the way campus maintenance problems are reported, tracked, and resolved.

Built specifically with Parul University's Goa campus in mind, Campus Care bridges the communication gap between students and maintenance staff.

Instead of complaints getting lost in WhatsApp groups or informal conversations, students can report issues such as:

💡 Flickering or broken lights
📽️ Faulty projectors
🚰 Plumbing and water-related issues
⚡ Electrical problems
🪑 Damaged furniture
🏫 Other campus maintenance concerns

Students can track the complete lifecycle of their complaints, while caretakers get a centralized dashboard to manage, prioritize, and resolve issues efficiently.

Report an issue. Track its progress. See it resolved.

…

View on GitHub

How I Built It

To build a scalable, responsive, and production-ready platform within a single weekend, I leveraged modern web technologies and powerful backend-as-a-service tools.

Frontend: Built using Next.js (App Router) and React, with dedicated routes such as /pending, /working, /completed, and /admin to provide focused dashboards for each stage of the issue-resolution lifecycle.
UI & Styling: Used Tailwind CSS to create a clean, responsive interface while Lucide React provided lightweight, scalable icons throughout the platform.
Backend & Database: Powered by Supabase and PostgreSQL, which handles the core application data and real-time workflow.
The issues and notifications tables manage issue status, updates, and user notifications.
Supabase Storage handles image uploads, including photos submitted with student complaints and resolution-proof images uploaded by maintenance staff.
The Next.js frontend communicates directly with Supabase, while Row Level Security (RLS) policies help ensure that data can only be accessed or modified by authorized users.
Authentication & Access Control: Integrated Supabase Auth for secure student registration and login. Role-based redirection ensures that maintenance staff can access their protected admin dashboard, while students are directed to the appropriate user interface.

This stack allowed me to move quickly from idea → functional prototype → deployable platform, while keeping the architecture flexible enough to scale as campus usage grows.

Why Does Open Innovation Matter?

Open innovation made it possible to build Campus Care as a solo student developer within a day, using modern, accessible technologies that make powerful development tools available to individuals.

The project is designed to be open and extensible, allowing future developers to build upon it, contribute features such as AI-powered issue triage, or adapt the platform for their own campuses. What starts as a solution for one campus can grow into a resource for institutions everywhere.