InboxSherpa: A Privacy-First AI Email Assistant for Small Shops

Aman Mondal — Sun, 18 Oct 2026 13:52:37 +0000

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

What I Built

InboxSherpa is a privacy-focused AI assistant for small shops and solo sellers who spend too much time answering customer support emails.

Paste a customer email and your shop's policy, and InboxSherpa classifies the message as Shipping, Refund, or General, summarizes the issue, and drafts a reply based on the provided policy. The reply can be edited and copied before sending. It doesn't send emails automatically.

It's designed for small businesses that want to spend less time on repetitive support replies without handing customer messages to a third-party AI API.

Demo

Code

Aman-Mondal / InboxSherpa

InboxSherpa

A privacy-first AI assistant for customer-support email triage.

InboxSherpa helps small businesses make sense of incoming customer emails and draft replies based on their own shop policies. It classifies a message, summarizes the customer's issue, and generates an editable response for a human to review.

Project status: MVP / Hacktoberfest Side Hustle challenge
AI model: Gemma 3 1B via Ollama
Current mode: Local inference on the machine running the backend

The problem

Small shops and solo sellers often spend time answering repetitive questions about shipping, refunds, and general support. InboxSherpa aims to reduce that busywork without automatically sending messages or taking decisions away from the business owner.

Features

Email triage: Categorizes messages as Shipping, Refund, or General.
Issue summary: Produces a short description of what the customer needs.
Policy-aware drafts: Uses the shop policies provided by the user to draft a reply.
Editable responses: Review and edit the generated…

View on GitHub

How I Built It

Frontend: React, Vite, CSS, and Lucide icons
Backend: Node.js and Express
AI: Gemma 3 1B through Ollama, running locally

The frontend sends the email and shop policy to the Express API. The backend passes them to the local Ollama model and returns a category, summary, and suggested reply.

The model is instructed to use the supplied policy and avoid inventing details. The user can review and edit the draft before using it.

Why Does Open Innovation Matter?

Using an open-weight model with local inference makes it possible to experiment without depending on a paid third-party AI API for every request. It also gives the shop owner more control over where customer email content is processed, since the current setup uses a local Ollama instance.

This is an early prototype, not a complete support platform. Local inference depends on the machine running the model, and drafts should always be checked before sending.

RambleQuest 🌿: Turning Open-Source AI into Real-World Adventures | Touch Grass Challenge

Aman Mondal — Sat, 10 Oct 2026 20:12:01 +0000

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

What I Built

RambleQuest is an AI-powered mini-adventure generator designed to get people away from their screens and into the real world.

The idea is simple: tell RambleQuest your interests, how much time you have, and your preferred difficulty. It generates a mini-adventure with actionable objectives that encourage you to explore your surroundings, notice things you usually overlook, and turn an ordinary walk into a small adventure.

Instead of using AI to generate more content for people to consume on a screen, RambleQuest uses AI to give them a reason to put the screen down.

Demo

Code

Aman-Mondal / RambleQuest

🌿 RambleQuest

Your next adventure is outside.

RambleQuest is an AI-powered mini-adventure generator designed to help people step away from their screens and reconnect with the world around them.

Tell RambleQuest about your interests, how much time you have, and your preferred difficulty. It generates a small, actionable quest that encourages you to explore your surroundings, notice the little things, and turn an ordinary day into a mini-adventure.

The goal is simple: less scrolling, more exploring.

✨ Features

🤖 AI-generated quests — Get personalized mini-adventures generated from your preferences.
⏱️ Flexible durations — Choose how much time you want to spend on your next adventure.
🎯 Customizable difficulty — Tailor quests to your preferred level of challenge.
📋 Actionable objectives — Break an adventure into manageable steps.
✅ Progress tracking — Check off objectives as you complete them.
🎨 Immersive interface — A warm, nature-inspired design built around the feeling…

View on GitHub

How I Built It

RambleQuest is built with React and Vite on the frontend, with Node.js and Express powering the backend API.

For local AI development, I used Ollama with Qwen 2.5 3B, an open-weight language model. The backend sends the user's preferences to a custom quest-generation prompt and asks the model to return structured quest data, including a title, description, objectives, and estimated duration.

The frontend presents the generated quest in an interactive interface where users can track their progress by checking off objectives.

The project was developed with a focus on keeping the experience simple: generate a quest, head outside, and complete it.

Why Does Open Innovation Matter?

Open innovation makes it possible for developers to experiment with AI without depending entirely on closed, proprietary systems.

Using an open-weight model through Ollama let me experiment with local inference on my own machine. This gave me more control over the development process and provided a path toward running AI without sending every prompt to a third-party inference provider.

For a project like RambleQuest, that matters because the goal is to encourage people to engage with the real world, not create another service that depends on constant online interaction.

Open models and accessible tools also make it easier for students and independent developers to build useful AI applications without needing an expensive infrastructure setup.

My Agent Session

I haven't included an agent session yet. I'll add a DevRelay session or link here if I have one available for the project.

Prize Categories

Best Use of ElevenLabs:
- The project demo features AI-generated narration created with ElevenLabs.
- The narration follows the user journey, from introducing RambleQuest and configuring a quest to completing objectives and reaching the final scoreboard.
Best Use of Render:
- RambleQuest's frontend and Express backend are deployed on Render.
- The deployment separates the React frontend from the backend API, providing a foundation for making the application publicly accessible.
Best Use of GitHub Copilot:
- GitHub Copilot assisted in developing RambleQuest, from implementing React components and styling the interface to debugging issues and refining the user experience.
- It supported iterative development, helping me troubleshoot problems, validate changes, and improve the application throughout the build process.

DEV Community: Aman Mondal

InboxSherpa: A Privacy-First AI Email Assistant for Small Shops

What I Built

Demo

Code

Aman-Mondal / InboxSherpa

InboxSherpa

The problem

Features

How I Built It

Why Does Open Innovation Matter?

RambleQuest 🌿: Turning Open-Source AI into Real-World Adventures | Touch Grass Challenge

What I Built

Demo

Code

Aman-Mondal / RambleQuest

🌿 RambleQuest

Your next adventure is outside.

✨ Features

How I Built It

Why Does Open Innovation Matter?

My Agent Session

Prize Categories