DEV Community: Aditya Nath Patel

Hustle AI

Aditya Nath Patel — Mon, 19 Oct 2026 04:45:36 +0000

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

What I Built

🌟 Core Vision & Philosophy

"Your AI. Your Business. Your Rules."
The platform automates high-frequency business operations while ensuring that private financial records, customer data, and sales numbers never leak to external cloud servers or get impacted by LLM hallucinations.

🛠️ The 5 Core Business Tools

Smart Listing Writer: Generates multi-marketplace titles, bullet points, and keyword SEO (for Amazon, Etsy, Shopify, eBay, and Local platforms) using local open-weight models via Ollama.
Invoice Studio & PDF: Features a real-time line-item calculator handling discounts and taxes using strict deterministic math (zero LLM errors) paired with instant branded PDF exports via ReportLab.
Receipt Organizer: A drag-and-drop OCR tool that parses vendor names, transaction dates, and totals using regex heuristics while flagging low-confidence fields for manual review.
Marketing Copywriter: Creates viral Instagram captions, WhatsApp promotional broadcasts, and festival campaigns in both English and Hindi with tone and length controls.
Business Email Writer: Drafts formal quotations, client follow-ups, payment reminders, and customer support resolutions with one-click clipboard copying.

📐 System Architecture & Tech Stack

Frontend (/frontend): Built with React 19, TypeScript, and Tailwind CSS, featuring an interactive landing page preview, theme toggle, and a live AI status indicator.
Backend (/backend): Built with FastAPI and Python 3.11+, acting as a secure API gateway with JWT authentication and a strict privacy dispatcher.
Storage: Powered by a local SQLite (or optional PostgreSQL) database for saved projects, invoices, and history, alongside a local folder keeping receipt uploads 100% on-device.
Dedicated Processing Engines:
AI Generation Engine: Defaults to local llama3.2:3b via Ollama with an air-gapped rule engine fallback.
Math & PDF Engine: Completely programmatic Python calculations for flawless invoicing.
OCR Engine: Clean and text-extraction parser for receipts.

🛡️ Key Technical Highlights

Privacy Modes: Supports a default Local Mode (air-gapped, zero telemetry) and an opt-in Remote Mode for custom OpenAI-compatible endpoints (like vLLM or OpenRouter).
Automated Testing Suite (/backend/tests): Includes comprehensive test coverage (pytest) validating exact mathematical precision in invoices, PDF byte stream generation, OCR heuristic parsing, and bilingual template generation.
Developer Experience: Includes Docker Compose configuration (docker-compose.yml), environment templates (.env.example), and quickstart launchers for Windows (run_dev.bat) and Unix (run_dev.sh).

Demo

https://github.com/adityanathpatel/HustleAI

Code

https://github.com/adityanathpatel/HustleAI

How I Built It

Frontend: Developed using React 19, TypeScript, and Tailwind CSS to create a responsive, theme-toggleable user interface.
Backend: Built with FastAPI and Python, serving as an API gateway with JWT authentication and a local privacy dispatcher.
Specialized Engines:
Separated creative tasks into local open-weight AI models via Ollama (Llama 3.2).
Used strict Python math and ReportLab for zero-error invoice calculations and PDF exports.
Implemented regex heuristics for receipt OCR text parsing.
Storage & Security: Utilized an on-device SQLite database and local folder storage to ensure 100% data sovereignty and an air-gapped workflow.

Why Does Open Innovation Matter?

Open innovation matters because no single company has all the best ideas or resources in-house. By collaborating with external developers, users, and partners, organizations can:

Speed up development instead of building everything from scratch.
Access specialized expertise and fresh perspectives beyond internal teams.
Lower R&D costs and share risks across a broader network.
Build customer-centric products through direct co-creation and real-world feedback.

Prize Categories

For HustleAI,

Open Source / Open Innovation (Utilizes local open-weight models via Ollama and an MIT-licensed architecture)
AI & Machine Learning / Productivity (A local business copilot with automated listing generation, OCR, and invoice tools)
Privacy & Security / Data Sovereignty (Air-gapped architecture with zero cloud telemetry and 100% on-device storage)

TouchGrass AI: Plan less, explore more.

Aditya Nath Patel — Sun, 11 Oct 2026 11:25:51 +0000

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

What I Built

What TouchGrass AI Does

TouchGrass AI is a privacy-first, offline-first outdoor adventure companion designed to minimize screen time while helping you explore the physical world. It guides your walks using deterministic mapping and local open-weight AI rather than keeping you hooked on an addictive interface.

The end-to-end adventure cycle includes:

Rapid Adventure Planning: Tailors a walk in 30 seconds based on your schedule, fitness level, and interests, generating custom sensory missions and safety checklists.
Reliable Offline Routing: Caches verified route geometry and quests directly into device storage via OpenStreetMap and OSRM with zero hallucinations or fake coordinates.
Minimalist Outdoor Mode: Transforms your interface into a pocket-first screen showing only a walk timer and active missions so you can put your phone away.
Field Observations: Lets you snap photos using a field viewfinder with a rule-of-thirds grid and record voice notes via in-browser speech recognition.
AI Digital Scrapbook: Synthesizes your route, completed missions, photos, and voice notes into a vintage journal complete with a field narrative and 1-click Markdown export.

Does It Get People Off the Screen and Into the World?

Yes, fundamentally. Its core design philosophy revolves around making the screen the shortest part of the experience. Instead of functioning as an endless social feed or SaaS dashboard, it uses a "pocket-first" approach:

It actively encourages you to put your phone in your pocket during the walk via a distraction-free Outdoor Mode.
It replaces mindless scrolling with tactile engagement through active sensory prompts (e.g., listening for birds or finding specific textures).
It shifts the digital interaction to after the walk, using local AI to turn your real-world offline experiences into a digital scrapbook journal.

Who Is It For?

Digital Minimalists & Tech Workers: Individuals looking for a intentional, low-distraction tool to unplug and step away from notification noise.
Nature Enthusiasts & Explorers: People who want structured walking loops, sensory quests, and trail guides without relying on cloud-tracking fitness apps.
Privacy Advocates: Users who want 100% local data control—ensuring location traces, photos, and voice notes never leave their device thanks to zero-cloud telemetry and edge AI models like Gemma 2 and Whisper.

Code

You can explore the complete codebase, backend logic, frontend architecture, and setup instructions directly via the repository here:

TouchGrassAI Repository on GitHub

How I Built It

TouchGrass AI combines lightweight open-weight models, deterministic routing infrastructure, and a local-first software architecture to balance offline autonomy with zero-cloud telemetry.

🤖 Open-Source AI & Models

Text & Reasoning Engine: Powered by Google DeepMind Gemma 2 (2B) via Ollama, handling dynamic workout parameterization, personalized sensory quest generation, and safety checklist formatting.
Vision & Field Identification: Uses Moondream (an edge vision-language model) running locally to process field photos and classify nature, flora, and wildlife observations.
Voice & Transcription: Integrated with speech-to-text processing for recording field audio notes completely hands-free on-device.
Zero-Dependency Fallback: Built with a deterministic rule-based fallback engine so the app remains fully functional even if local AI services are turned off or unavailable.

🗺️ Infrastructure & Routing

Deterministic Geometry: Relies strictly on OpenStreetMap (OSM) and Project OSRM for routing data. This ensures all generated tracks, loops, and trails use physical pathways without hallucinations or fake coordinates.

⚙️ Software Architecture & Frameworks

Backend: Built using FastAPI (Python) to manage API endpoints, route geometry requests, and local database handling.
Frontend: A React + TypeScript + Vite progressive web app (PWA) structured for high performance and responsiveness.
Offline Storage: Utilizes browser-based IndexedDB alongside a Service Worker to cache complete adventure packets (routes, quests, and observation schemas) for total offline usage and Airplane Mode compatibility.
Data Storage: Uses a local SQLite database (touchgrass.db) to preserve a strict privacy boundary with zero cloud tracking or telemetry.

Why Does Open Innovation Matter?

Open innovation is essential for building technology that respects human attention and data sovereignty. It champions transparency, community-driven progress, and the fundamental right to own your stack without being locked into proprietary ecosystems.

For TouchGrass AI, open innovation isn't just a development preference—it is an architectural necessity. Here is why it matters and what it makes possible:

🚀 What Open Innovation Made Possible

100% Offline Capability & Airplane Mode Reliability
Closed APIs: Require persistent cloud connectivity, streaming tokens back and forth over cellular networks. If you wander into a dead zone, a park, or a mountain trail, a closed cloud app breaks down entirely.
Open Innovation: Running open-weight models locally via Ollama means the entire inference and routing engine lives on the device. You can turn on Airplane Mode, walk deep into nature, and still have fully functional AI quest generation and routing.
Absolute Zero-Telemetry Privacy
Closed APIs: Inevitably ingest user telemetry, location traces, photos, and voice memos to train corporate models. For an app designed around personal wellness and outdoor exploration, piping your physical location and journal entries to a third-party server defeats the purpose of unplugging.
Open Innovation: Keeps all personal data strictly local inside SQLite and IndexedDB. Your walks, photos, and voice notes never leave your hardware.
Deterministic Physical Grounding (Zero Hallucinations)
Closed APIs: Proprietary mapping or generalized LLMs are prone to hallucinating paths, recommending impassable routes, or inventing fake coordinates.
Open Innovation: Leveraging OpenStreetMap and OSRM guarantees deterministic, community-verified geographical geometry. You get real pathways, physical loops, and trails you can actually walk safely.
Full Hackability and Extensibility
Open sourcing the repository under an MIT License means anyone can inspect the codebase, audit the privacy safeguards, add custom local models, or tailor new sensory quest packs for their local geography.

Prize Categories

TouchGrass AI aligns with several impact and technology partner categories, specifically designed around edge-deployed open-weight models and offline-first community resilience:

Global Resilience (Impact Track): Focuses on building offline, edge-based systems and resilient tools for outdoor or low-connectivity environments.
Ollama (Special Technology Prize): Showcases local open-weight execution using Ollama to drive edge inference (utilizing Gemma 2 and Moondream).
Local / On-Device Intelligence & Offline-First: Highlights architectures that eliminate cloud dependencies to ensure complete user privacy and field reliability in remote areas.

Campus Diary

Aditya Nath Patel — Sun, 04 Oct 2026 13:16:31 +0000

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

What I Built

I built Campus-Diary, a web application designed as a centralized platform for college organizations and student communities.

Core Purpose

It replaces fragmented tools (like scattered group chats and spreadsheets) by unifying club management into a single platform to automate event workflows, manage member directories, and streamline campus communications.

Key Features

Event Management & Automation: Create, schedule, and manage campus events and timelines.
Member Directory: Track and manage club members, roles, and responsibilities in one portal.
Unified Communication: Centralize operational updates to keep members and stakeholders informed.
Operational Transparency: Activity tracking for organizational clarity.

Tech Stack

Frontend: React
Build Tool: Vite
Styling: Tailwind CSS
Code Quality: ESLint

Demo

https://adityanathpatel.github.io/Campus-Diary/

Code

https://github.com/adityanathpatel/Campus-Diary

How I Built It

I built Campus-Diary as a client-side single-page application (SPA) using a modern JavaScript workflow.

1. Project Scaffolding & Build Tooling

Vite: Used as the build tool and development server, replacing traditional, heavier bundlers like Webpack to provide fast Hot Module Replacement (HMR) and optimized production builds via Rollup.
Node.js & npm: Managed dependencies and package scripts (package.json and package-lock.json).

2. Core User Interface & Components

React: Serves as the primary frontend UI framework, structured using component-based architecture to render views like event schedules, member lists, and communication feeds dynamically.
HTML Entry Point: index.html acts as the single page root where the React application mounts.

3. Styling & Design

Tailwind CSS: Utility-first CSS framework configured via tailwind.config.js and postcss.config.js to style UI components rapidly without writing custom CSS files.

4. Code Standards & Linting

ESLint: Configured via eslint.config.js to enforce code quality, consistent formatting, and prevent common JavaScript/React errors.

Development & Build Lifecycle

Development: Running npm run dev starts the Vite dev server locally at http://localhost:5173.
Quality Control: Executing npm run lint scans the project files for syntax errors or anti-patterns.
Production Build: Running npm run build bundles, minifies, and optimizes your React code into static assets inside a dist/ directory ready for deployment.

Why Does Open Innovation Matter?

Open innovation matters because modern organizations can no longer rely solely on their internal R&D to stay competitive. Coined by management scholar Henry Chesbrough, open innovation is the practice of leveraging external ideas, technologies, and pathways to market alongside internal resources.

Here is why it has become a critical strategic driver across industries:

1. Accelerated Time-to-Market

By integrating external technologies, pre-existing research, or third-party solutions, organizations avoid "reinventing the wheel." This significantly shortens product development cycles and allows companies to launch features or products faster than relying on internal resources alone.

2. Reduced R&D Costs and Risk

Internal R&D involves high upfront costs and financial risk. Open innovation allows companies to share development costs and risks with partners, startups, academic institutions, or supplier networks. Failing fast and cheaply during early-stage experiments with external partners preserves capital.

3. Access to Global Talent and Diverse Perspectives

No single organization holds all the top talent in a given field. Tap into crowdsourcing platforms, hackathons, and research partnerships to access global expertise, specialized skills, and diverse problem-solving approaches that internal teams might lack due to groupthink or organizational silos.

4. New Revenue Streams and Monetization

Open innovation works in both directions (inbound and outbound):

Inbound: Bringing external ideas into the firm.
Outbound: Commercializing internally developed technology or IP that doesn't fit the core business through licensing, spin-offs, or joint ventures, turning underutilized assets into new revenue.

5. Adaptability to Rapid Technological Change

With technological shifts occurring faster than ever (e.g., AI, biotech, clean energy), staying agile is essential. Open innovation builds an ecosystem around a company, making it easier to sense market shifts, adopt emerging technology stack integrations, and adapt business models rapidly.

Common Frameworks of Open Innovation

Model	Description	Example
Inbound	Sourcing ideas, technology, or IP from outside	P&G's Connect+Develop program
Outbound	Licensing or selling internal IP/technology externally	Tech companies licensing proprietary patents
Co-creation	Collaborating directly with customers or partners	LEGO Ideas platform for user-submitted designs
Ecosystems	Building platforms where third parties develop complementary products	Apple App Store or Android Developer Network

Hi! This is my first post to the dev.

Aditya Nath Patel — Fri, 02 Oct 2026 18:18:07 +0000