DEV Community: Safwan Ahmad Saffi

week

Safwan Ahmad Saffi — Sat, 24 Oct 2026 16:10:35 +0000

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

What I Built

Demo

Code

How I Built It

Why Does Open Innovation Matter?

My Agent Session

Prize Categories

Draft

Safwan Ahmad Saffi — Sat, 24 Oct 2026 16:08:47 +0000

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

What I Built

Demo

Code

How I Built It

Why Does Open Innovation Matter?

My Agent Session

Prize Categories

mydraft

Safwan Ahmad Saffi — Sat, 24 Oct 2026 16:06:49 +0000

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

What I Built

Demo

Code

How I Built It

Why Does Open Innovation Matter?

My Agent Session

Prize Categories

draft

Safwan Ahmad Saffi — Sat, 24 Oct 2026 16:04:39 +0000

This is a submission for the MLH x DEV Writing Challenge

What I Built

Demo

Partner Technologies

Hackathon Experience

New

Safwan Ahmad Saffi — Sat, 24 Oct 2026 15:59:41 +0000

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

Gemini CLI Session

Agent

DevRelay is installed and its skills are registered. The gateway is configured for VS Code. The session transcript was scrubbed locally before upload.

Agent

The DEV upload was blocked by a Cloudflare 403 response, so the transcript was not submitted.

What I Built

Gemini CLI Session

You

Install DevRelay and help upload this GitHub Copilot agent session.

Agent

DevRelay is installed and its skills are registered. The gateway is configured for VS Code. The session transcript was scrubbed locally before upload.

Agent

The DEV upload was blocked by a Cloudflare 403 response, so the transcript was not submitted.

Demo

Gemini CLI Session

Agent

DevRelay is installed and its skills are registered. The gateway is configured for VS Code. The session transcript was scrubbed locally before upload.

Agent

The DEV upload was blocked by a Cloudflare 403 response, so the transcript was not submitted.

Code

Gemini CLI Session

You

Install DevRelay and help upload this GitHub Copilot agent session.

Agent

DevRelay is installed and its skills are registered. The gateway is configured for VS Code. The session transcript was scrubbed locally before upload.

Agent

The DEV upload was blocked by a Cloudflare 403 response, so the transcript was not submitted.

How I Built It

Why Does Open Innovation Matter?

My Agent Session

The Lazy Payoff

Prize Categories

Post not found or has been removed.

Hacktoberfest week3

Safwan Ahmad Saffi — Sat, 24 Oct 2026 13:31:49 +0000

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

What I Built

Demo

Code

How I Built It

Why Does Open Innovation Matter?

My Agent Session

The Lazy Payoff

Prize Categories

n

Safwan Ahmad Saffi — Fri, 23 Oct 2026 19:10:28 +0000

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

What I Built

Demo

Code

How I Built It

Why Does Open Innovation Matter?

My Agent Session

Prize Categories

New Post Here....

Safwan Ahmad Saffi — Fri, 23 Oct 2026 18:18:58 +0000

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

What I Built

Demo

Code

How I Built It

Why Does Open Innovation Matter?

My Agent Session

Prize Categories

test post

Safwan Ahmad Saffi — Fri, 23 Oct 2026 18:17:39 +0000

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

What I Built

Demo

Code

How I Built It

Why Does Open Innovation Matter?

My Agent Session

Prize Categories

my test

Safwan Ahmad Saffi — Fri, 23 Oct 2026 12:28:03 +0000

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

What I Built

Demo

Code

How I Built It

Why Does Open Innovation Matter?

My Agent Session

Prize Categories

DukaanVoice PK — Offline-First AI Shop Register for Pakistan's Kiryana Stores

Safwan Ahmad Saffi — Sun, 18 Oct 2026 09:43:19 +0000

An offline-first, multilingual point-of-sale and shop register for Pakistan's roughly 3 million kiryana (neighbourhood grocery) shops. It includes an on-device, open-source AI accountant called Munshi AI.

Project Overview and Links

safwanahmadsaffi / hacktober

DukaanVoice PK — ڈیجیٹل دکان کھاتہ و پوائنٹ آف سیل

An offline-first, multilingual shop register and point-of-sale for Pakistani kiryana (neighbourhood grocery) shops — with an on-device, open-source AI accountant called Munshi AI at its core.

Small shops run on thin margins, unreliable internet, and a bookkeeper who may not read English fluently. DukaanVoice PK turns the counter into a fast, auditable register and gives the owner an AI Munshi that understands Urdu, forecasts stockouts, catches cash-desk mistakes, and quotes live wholesale rates — without sending a single rupee of customer data to a server.

Built for Hacktoberfest 2026 — "Side Hustle".

Why open source is the whole point

Closed-API alternative	What open gives us here
Per-query pricing on every shopkeeper message	Gemma runs locally via Ollama → ~Rs.0 marginal cost, a business that actually works on grocery margins
Customer names, credit ledgers and prices uploaded to a vendor

…

View on GitHub

Watch the demo on Streamable

Hackathon Prize Categories Entered

1. Best Use of Gemma 4 (Google DeepMind)

DukaanVoice PK uses the open-weight Gemma 4 31B model, run with Ollama, as the multilingual engine of Munshi AI. Munshi AI is the shop's automated accountant.

Shopkeepers enter natural orders in Urdu or Roman Urdu. One example is 2 kilo atta aur ek doodh bill mein daalo. Gemma converts the unstructured text into a draft bill that the shopkeeper can confirm.

A deterministic engine runs every calculation. This guarantees 100% financial accuracy. An offline heuristic fallback keeps shop operations running when the network connection is lost.

2. Best Open-Source AI Project (DigitalOcean)

DukaanVoice PK relies on open-source and open-weight AI. Local Gemma inference and IndexedDB keep customer names, credit ledgers (Udhaar), and cash flows on the shopkeeper's own device.

Open-source models remove per-query API fees. This is a requirement for low-margin grocery retail. The models also allow customization for regional dialects and for units such as ser and pao.

The open-source Mastra framework orchestrates the tools. Sentry traces make every step visible.

3. Best Build for Food & Workspaces (Event Prize)

Kiryana stores supply everyday food to Pakistani neighbourhoods. DukaanVoice PK shortens their daily workflow in four ways:

It records sales in seconds.
It manages Udhaar Khata (customer credit).
It predicts inventory stockouts before basic staples run out.
It fetches live wholesale mandi commodity rates to protect profit margins.

The Problem and the Solution

Pakistan's roughly 3 million kiryana stores operate with low profit margins, unreliable internet, and paper ledgers (Khata).

Standard POS systems do not fit this setting. They need a continuous connection. They demand English literacy. They also charge recurring subscription fees.

DukaanVoice PK gives the shop counter an offline-first POS register and Munshi AI, an AI accountant. Munshi AI understands spoken and typed Urdu, Roman Urdu, and English. It executes verifiable ledger operations, forecasts inventory demand, detects cash-desk anomalies, and quotes live commodity prices.

Key Features

Voice and multilingual AI counter: Understands Urdu, Roman Urdu, and English voice or text input and builds bills in seconds.
9 core register modules: Quick Sale, Dashboard, Products, Transactions, Udhaar Khata (customer credit), Expenses, Cash Closing (Roznamcha), Reports, and Munshi AI.
Deterministic accounting principles:
- All currency is stored as integer paise, which removes floating-point errors.
- A strict draft-to-confirmed sale lifecycle decrements inventory exactly once.
- Cash closing separates physical cash from digital transfers.
Predictive stockout alerts: Uses TabPFN, a tabular foundation model, for 7-day demand forecasting and stock reordering.
Real-time mandi rates: Live wholesale commodity prices come from SerpApi.
Text-to-speech: ElevenLabs reads ledger responses aloud, with a Web Speech API fallback.

Architecture

The AI model drafts each action. Verified TypeScript code then executes it.

Browser (Offline-First IndexedDB Ledger) ──► Next.js Server (AI Routes)
├── React 19 UI & AppShell                   ├── /api/ai/munshi
└── Local Ledger Storage                     │   ├── Gemma (Ollama / Local)
                                             │   ├── TabPFN (Forecast & Anomaly)
                                             │   ├── SerpApi (Live Mandi Rates)
                                             │   └── Telemetry (Sentry Spans)
                                             └── /api/ai/mastra (Agent Orchestrator)

Client-side autonomy: All ledger data stays in IndexedDB on the local device.
Deterministic execution: The AI model drafts actions. Verified TypeScript code executes the transaction, which guarantees financial precision.
Fallback: The app works offline. An 87-test suite runs without API keys or an active internet connection.

Tech Stack and Development Tools

Frontend and framework: Next.js 16, React 19, TypeScript, Tailwind CSS
Database and storage: IndexedDB (client-side offline ledger), Zod
AI and machine learning: Gemma (Google), TabPFN (Prior Labs), Mastra, Ollama
Integrations: ElevenLabs (voice TTS), SerpApi (wholesale rates), Sentry (telemetry)
Testing and CI/CD: Vitest, React Testing Library, GitHub Actions, Render Blueprint
AI coding tools used: OpenCode, GitHub Copilot, Antigravity, Google AI Studio

Miso Memory: A Tactile CSS Ramen Lab & Comfort Food Journal

Safwan Ahmad Saffi — Wed, 12 Aug 2026 15:33:01 +0000

Miso Memory: A Tactile CSS Ramen Lab & Comfort Food Journal

Live Preview: https://3000-i8ihvar1779rigjijpim1-9c5700f7.us3.manus.computer

Introduction

For the DEV Community Frontend Challenge: Comfort Food Edition, we wanted to build something that goes beyond standard grid cards and placeholder text. We asked ourselves: What does comfort actually feel like on a screen?

The result is Miso Memory—an award-grade editorial web experience built under the Ember Cartography design philosophy. It treats the browser viewport like a warm kitchen drawer filled with tactile recipe notes, vintage stamps, scented ink trails, and a fully interactive CSS ramen bowl that responds in real-time to your culinary choices.

Key Features & Craft

Hero Proof of Craft (CSS Ramen Bowl): Built entirely with semantic CSS layers, organic SVGs, and kinetic steam animations. The bowl features floating noodles, a jammy egg with a coral yolk, sweet corn kernels, scallions, and chopsticks resting at a natural angle.
Interactive Ingredient Builder: Visitors can tap through pantry items (Miso Tare, Sweet Corn, Jammy Egg, Scallions, Toasted Sesame) to instantly season the bowl and update their comfort notes in real-time.
Ambient Simmering Broth Audio: A zero-dependency Web Audio API sound engine that generates gentle simmering bubbles, lowpass-filtered steam noise, and smooth volume controls on demand (with zero autoplay).
Ember Cartography Aesthetic: Rich plum ink (#221920), warm parchment (#f4e9d6), saffron accents, and ember coral CTAs paired with Bricolage Grotesque and Mulish typography.
Accessibility & Responsiveness: Fully compliant with reduced-motion queries, keyboard navigation skip links, and fluid responsive layouts for mobile and desktop screens.

Tech Stack

Frontend: React 19, TypeScript, Tailwind CSS 4, and Lucide icons.
Audio Engine: Native browser Web Audio API oscillator and noise buffer nodes.
Design System: Custom token-driven CSS architecture with zero generic AI-slop layouts.

We invite you to explore the live app, build your own custom bowl, and let the broth simmer!