DEV Community: vedant satbhai

InterruptIQ — Attention Gateway & Focus Intelligence Platform

vedant satbhai — Sun, 25 Oct 2026 19:03:17 +0000

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

What I Built

InterruptIQ — Attention Gateway & Focus Intelligence Platform 🧠⚡

InterruptIQ helps engineering teams protect their focus by evaluating when notifications should be delivered, delayed, or batched instead of interrupting developers constantly.

Its Focus Report (Shadow Mode v0) analyzes interruption patterns and simulates notification policies without modifying real messages.

Key features include:

🧠 Focus-state inference using calendar boundaries and activity patterns.
⚡ Deterministic, explainable notification policies.
📊 Focus reports and an interactive policy simulator.
🔍 User feedback on potentially harmful notification delays.
🤖 An AI-assisted architecture for offline decision evaluation.

Demo

GitHub Repository

Code

Explore the source code: InterruptIQ on GitHub

Built with TypeScript, Fastify, React, Vite, Prisma, PostgreSQL, Redis, and Docker.

How I Built It

I built InterruptIQ as a TypeScript monorepo with a Fastify backend, React simulator, and shared domain logic.

The core policy engine uses deterministic rules to evaluate focus states and notification timing. The architecture also includes a local embedding-engine package and supports an offline AI-critique approach for evaluating historical decisions.

I chose shadow mode first so the system can evaluate potential benefits and risks before any live notification handling is introduced.

Why Does Open Innovation Matter?

Open source makes notification decisions transparent, testable, and adaptable. Developers can inspect the rules, evaluate privacy practices, experiment with local AI models, and contribute improvements without depending entirely on a closed platform.

My Agent Session

Not linked yet.

The Lazy Payoff

InterruptIQ aims to reduce unnecessary context switching and manual notification management, giving developers more uninterrupted time for deep work.

Rather than claiming unmeasured time savings, the Focus Report is designed to evaluate potential benefits alongside user feedback about harmful delays.

Prize Categories

Open-Source AI
Developer Productivity / Developer Tools

I’ll verify the official partner-category names and eligibility before final submission.

Built by @vedant21-ctr

InterruptIQ — Protect attention. Preserve context.

🛡️ Ruko: Stop. Check Before You Tap

vedant satbhai — Mon, 19 Oct 2026 06:35:21 +0000

Submission for the Hacktoberfest Open-Source AI Challenge — Week 2: Side Hustle

🚀 What I Built

Ruko is a privacy-first AI assistant that helps people identify suspicious SMS messages, understand scam warning signs, and make safer decisions. The core safety checker is free, with potential paid family and small-business setup services.

🎬 Demo

https://drive.google.com/drive/folders/1h7UnWrpRNzhmHBeUbQY-W3ahjW_VG_Ix?usp=drive_link

💻 Code

GitHub: https://github.com/vedant21-ctr/rukoAI

⚙️ How I Built It

Built with Python, FastAPI, Next.js, TypeScript, Streamlit, Ollama, and Gemma 2B.

Ruko combines a privacy gate, safe structured signals, deterministic risk scoring, local AI explanations, and a safety validator. It also includes an interactive educational lab and a development-only subscription simulation.

🌍 Why Open Innovation Matters

Local inference helps keep message content on the user's device and reduces dependence on paid cloud AI APIs. Open-weight models also give developers more control over model selection and experimentation.

👤 My First User

Ruko is ready for demonstration, but real-user feedback and willingness to pay still need validation. No paying customers are claimed yet.

🏆 Prize Categories

Gemma: Local Gemma 2B integration via Ollama.
Overall Side Hustle Challenge: Privacy-first AI with a potential commercial model.

📊 Evaluation

The current hybrid benchmark achieved 82.54% recall and 61.86% accuracy on 118 classified samples. False positives remain a major limitation, and improving detection quality is a priority.

The project reports 71 passing tests and a successful Next.js production build.

Building Ruko has reinforced one principle: AI security tools need privacy, transparent evaluation, and safe fallbacks—not just a model that produces convincing answers.

Stop. Check before you tap. 🛡️

devchallenge #hf26challenge #Hacktoberfest #OpenSourceAI #Gemma

HaveCrops Analytics: Growing Smarter with AI | Hacktoberfest 2026

vedant satbhai — Mon, 12 Oct 2026 03:23:10 +0000

*# 🌿 HaveCrops Analytics — Hacktoberfest Week 1: Touch Grass

What I Built

HaveCrops Analytics is an AI-powered agricultural analytics platform that helps turn crop and environmental data into useful farming insights. 🌱

Demo

🚜 https://havecrops.streamlit.app/

Code

💻 https://github.com/vedant21-ctr/helcrops

How I Built It

Built using Python, Streamlit, Scikit-learn, LangGraph, FAISS, and Llama 3.3. It combines machine learning predictions, RAG-based knowledge retrieval, interactive visualisations, and AI-generated agricultural advisory reports.

Why Does Open Innovation Matter?

Open source makes AI accessible, encourages collaboration, and allows developers to build tools that solve real-world problems. With Touch Grass, I wanted to connect technology with something grounded in the real world: agriculture and nature. 🌾

Hacktoberfest #OpenSource #AI #MachineLearning #TouchGrass

[Boost]

vedant satbhai — Mon, 05 Oct 2026 19:38:19 +0000

Hacktoberfest Weekend Challenge: Build for a Friend Submission 🤝

vedant satbhai

Oct 5

Ruko — Stop. Check Before You Tap. रुको.

#devchallenge #weekendchallenge #hf26challenge

2 min read

Ruko — Stop. Check Before You Tap. रुको.

vedant satbhai — Mon, 05 Oct 2026 06:40:25 +0000

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

What I Built

Ruko — Stop. Check before you tap. रुको.

I built Ruko as a privacy-first second opinion for people who receive suspicious messages and aren't sure what to do next.

The idea came from a simple problem: scam messages don't always look like scams. A message can look like it's from a bank, a courier company, a job recruiter, or a buyer on a marketplace. When someone is unsure, the easiest thing to do is tap the link, reply, pay, or share information.

Ruko is designed to create one small pause before that happens.

You paste a suspicious message into Ruko and it:

checks the message using deterministic safety rules
identifies suspicious signals such as urgency, payment requests, impersonation, and suspicious links
shows exactly what was detected
uses Google's open-weight Gemma model locally for context and explanation
gives a simple, actionable next step
refuses to send sensitive authentication messages to the AI layer

The most important part is what Ruko doesn't do.

If a message looks like it contains an OTP, PIN, password, CVV, or authentication code, Ruko's Privacy Gate stops processing before Gemma is called.

Instead, Ruko clearly says:

RUKO STOPPED HERE

This makes the privacy boundary visible instead of hiding it.

The goal is simple:

Stop. Check before you tap.

Built for a friend. Useful for everyone.

Demo

🎥 Video demo: https://drive.google.com/drive/folders/1m_k6TyTNtXnEJKM_K30DE8bilaaJysTP?usp=sharing

The demo shows three situations:

A bank/KYC scam message being analyzed and flagged as HIGH RISK
The X-Ray view showing the signals Ruko detected
A private OTP message being blocked by the Privacy Gate before it reaches Gemma

Code

GitHub: https://github.com/vedant21-ctr/rukoAI

The repository contains the complete project, including:

Next.js frontend
FastAPI backend
Privacy Gate
Safe representation layer
deterministic rule engine
local Gemma integration
Safety Validator
evaluation benchmarks
automated tests
architecture and privacy documentation

How I Built It

Ruko is built around Gemma, Google's open-weight model, running locally through Ollama.

The architecture deliberately separates safety decisions from AI-generated explanations:

Message → Privacy Gate → Safe Representation → Rule Engine → Gemma → Safety Validator → Ruko warning

The Privacy Gate runs first.

Instead of sending the original message directly to the model, Ruko converts safe messages into a structured representation containing signals such as:


json
{
  "intent": "account_warning",
  "urgency": "high",
  "requested_action": "verify_identity",
  "payment_requested": false,
  "credential_requested": false,
  "url_type": "shortened",
  "threat_present": true,
  "sender_type": "unknown"
}

Building Ruko for a Friend

vedant satbhai — Mon, 05 Oct 2026 03:27:50 +0000

I'm participating in the Hacktoberfest Weekend Challenge: Build for a Friend.

For this challenge, I'm building Ruko — “Stop. Check before you tap.”

Ruko is a privacy-first scam warning assistant designed for someone close to me who may receive suspicious SMS or WhatsApp messages.

The idea is simple:

Before you tap a link, share information, or make a payment — stop and check.

I'm building it with open-source AI (Gemma) running locally, with a privacy layer that prevents sensitive information such as OTPs, PINs, passwords, and CVVs from being sent to the AI model.

I'm excited to build something practical for a real person while exploring how open-source AI can be used for privacy-focused applications.

Let's build. 🚀