DEV Community: Mohammed Faisal Bagban

Lazylist-AI

Mohammed Faisal Bagban — Sat, 24 Oct 2026 15:48:55 +0000

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

What I Built

I built LazyList AI — a tranquil, minimalist task trimmer designed for anyone suffering from to-do list paralysis and productivity burnout.

The Problem

Traditional productivity apps make you work for them instead of working for you. You write down 35 tasks, get overwhelmed by high-priority flags, spend 45 minutes color-coding tags, and end up paralyzed by decision fatigue.

The Solution: "Do less. Stress less. 🦥"

LazyList AI takes your raw brain dump and gently categorizes your items into exactly three realistic, stress-free buckets:

⚡ Do Now: Time-sensitive, high-impact tasks (e.g., today's bills, urgent client bugs, deadlines).
🌿 Do Later: Thoughtful, important tasks that have no business stressing you out today.
🦥 Skip or Simplify: Overcomplicated rabbit holes, low-leverage busywork, and perfectionist traps that you can happily drop or shrink.

Who gets to be lazier?

Developers, students, and busy professionals who just want to know the 2–3 things that actually matter today without spiraling into productivity guilt.

Demo

🌐 Live Web App: https://slow-and-steady-phi.vercel.app
⚡ No setup required: Test it directly in any browser with the built-in "✨ Try Sample Tasks" button!

Code

MdFaisalDevops / slow-and-steady

🦥 LazyList AI

   (\_/)
  ( •_•)   "Do less. Stress less."
  / >🦥

Your tasks. Less stress.

A tranquil, lightweight task organizer built for the Slow and Steady hackathon.

🌐 Live Web App: https://slow-and-steady-phi.vercel.app
No installation or configuration needed — test it live right now!

📖 Table of Contents

🌿 Overview & Philosophy

Modern productivity tools are often loud, complex, and anxiety-inducing. Users dump 40 tasks into a backlog, feel paralyzed by the sheer volume, and fall into perfectionist burnout.

LazyList AI is the antidote. Built around the spirit of the Slow and Steady hackathon:

Ruthless Trimming: Not every task deserves your energy today.
Calm Prioritization: Instead…

View on GitHub

GitHub Repository: https://github.com/MdFaisalDevops/slow-and-steady
Tech Stack: Pure semantic HTML5, Vanilla CSS, and Vanilla JavaScript inside a single, zero-dependency index.html file.
Memory Footprint: < 5 MB in the browser. Zero build tools, zero npm packages, zero React, and zero database.

How I Built It

The theme of the challenge was "Slow and Steady", and I took that philosophy to heart across both the UI and the AI architecture.

1. Genuine Open-Weight AI (`qwen2.5:0.5b`)

I integrated Alibaba Cloud’s compact open-weight model qwen2.5:0.5b via a local Ollama instance:

Ultra-Lightweight: The model is only ~398 MB and runs with near-zero latency even on modest CPU hardware.
Structured JSON Schema: The model is prompted with a strict schema to output valid JSON matching our three categories (do_now, do_later, skip_or_simplify).
Decoupled Frontend: The frontend interacts with a dedicated, isolated function:

  async function sortTasksWithAI(rawTasks)

2. Transparent Dual-Engine Architecture

To ensure anyone evaluating the app can use it immediately without installing Ollama or any model:

Demo Mode (Default): A transparent, deterministic rule-based keyword heuristic classifier. It is explicitly labeled in the UI as 🌿 Demo Mode — Rule-based sorting — no smoke and mirrors, no pretending it's AI when it isn't.
Local Ollama Mode (Optional): When local Ollama is running with qwen2.5:0.5b, the app detects it or allows toggling with one click. If Ollama ever goes offline, the app seamlessly falls back to Demo Mode without throwing errors or breaking the user experience.

3. Tranquil Design System

Warm soothing cream canvas (#FAF7F2) with forest and sage green accents (#3F704D, #EBF3ED).
Rounded cards, smooth strikethrough task completion animations, and a calming swaying sloth loader.
One-click 📋 Copy Results button to copy formatted markdown task lists to the clipboard.

Why Does Open Innovation Matter?

Open innovation and open-weight models are game-changers for everyday productivity apps:

Absolute Privacy for Sensitive Brain Dumps:

Your personal daily to-do list contains private medical appointments, financial bills, intimate thoughts, and confidential work items. With proprietary closed APIs (like OpenAI or Anthropic), you are forced to transmit private daily routines to external corporate servers. With an open-weight model like qwen2.5:0.5b running locally, your thoughts never leave your device.
Zero Cost & Democratization:

Closed APIs require credit cards, monthly subscriptions, and token metering. Open-weight models empower students, indie builders, and developers globally to build smart applications for $0.00.
Long-Term Digital Resilience:

If a closed API changes pricing, alters its terms of service, or deprecates an endpoint, closed apps break. Open innovation ensures that software remains functional and self-hosted forever.

My Agent Session

This project was built pair-programming with the Antigravity AI coding agent:

Collaboratively refined the design tokens (cream + soft green palette).
Architected the dual-engine sorting mechanism (sortTasksWithAI).
Designed the single-file zero-dependency HTML/CSS/JS structure.
Automated browser testing to verify validation alerts, loading states, task completions, and clipboard exports.
Automated git version control and deployed directly to Vercel.

The Lazy Payoff

Time saved: ~20 to 30 minutes every single morning.

Instead of agonizing over how to organize an overwhelming list:

Paste all messy thoughts into LazyList AI.
Click Sort My Tasks 🦥.
In under 500 milliseconds, you get:
- 2 or 3 genuine priorities under Do Now.
- A guilt-free deferred bucket under Do Later.
- An explicit license to drop perfectionist time-sinks under Skip or Simplify.

The greatest lazy superpower isn't doing tasks faster — it's giving yourself permission not to do the pointless ones at all.

Prize Categories

Slow and Steady: Clean, deliberate, lightweight software built for calm productivity.
Open-Source / Open-Weight AI: Genuine local inference using qwen2.5:0.5b via Ollama with full offline resilience and transparent fallback.

DEV-fix-AI

Mohammed Faisal Bagban — Sun, 18 Oct 2026 14:30:44 +0000

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

🛠️ DevFix AI — Private DevOps Troubleshooting with Open-Weight AI

What I Built

DevFix AI is an AI-powered DevOps & Site Reliability Engineering (SRE) troubleshooting assistant designed for software engineers, DevOps practitioners, and small IT teams. It ingests complex infrastructure crash logs and instantly isolates the root cause, extracts verifiable log evidence, generates safe terminal diagnostic commands, and suggests remediation steps with rollback precautions.

Who Would Pay for It & What Problem Does It Solve?

Engineering teams face a high-stakes dilemma during production incidents:

The Closed Cloud AI Trap: Piping infrastructure logs into proprietary APIs (OpenAI, Claude) is dangerous. Logs contain sensitive organizational footprints: private IP subnets, database credentials, internal hostnames, and auth tokens. For regulated industries (healthcare, defense, fintech), this violates SOC 2, HIPAA, and GDPR. Furthermore, multi-thousand-line crash dumps incur unpredictable, high monthly token bills.
Traditional Playbooks: Searching documentation during a 2 AM outage is slow and disconnected from real-time stack traces.

DevFix AI solves this as a side-hustle product:

Zero Data Leakage: Powered by open-weight models (via Ollama) running locally on the engineer's machine or inside their private VPC.
Zero Per-Token Charges: Unlimited log diagnostics without recurring API invoices.
Enforced Safety: Commands are classified as Read-Only or Requires Sudo and strictly require human review before running—never auto-executing blindly in production.
Commercial Potential: A freemium self-hosted open-source core with proposed $19/seat team tiers offering shared remediation playbooks, Slack incident webhooks, and private team audit logs.

Demo

🌐 Live Web Application: https://d-evfix-ai-12ck-nu.vercel.app/
🔌 FastAPI Backend (Local/Docker): http://localhost:8000/docs

Note on Testing: The live Vercel app includes a built-in Deterministic Client Engine, allowing you to test real-world Kubernetes, Docker, Jenkins, Linux, Terraform, and AWS failures immediately out-of-the-box without configuring any API keys or local runtimes!

Code

MdFaisalDevops / DEvfix-Ai

🛠️ DevFix AI

AI-Powered DevOps & SRE Troubleshooting Assistant

Diagnose Infrastructure Errors with Open-Weight AI (Ollama) — 100% Private, Air-Gapped Ready & $0 Cloud Token Fees

🚀 Try the Live Web App on Vercel

Explore Features • Quickstart • Architecture • Supported Platforms • Deployment • Contributing

📌 Why DevFix AI?

Modern DevOps teams face a difficult dilemma during incidents:

Proprietary Cloud AI APIs (OpenAI, Claude): While smart, sending infrastructure logs to external APIs exposes sensitive internal hostnames, private IP subnets, database credentials, and trace IDs to third-party data centers. Furthermore, verbose multi-thousand-line crash logs result in unpredictable, exorbitant monthly token bills.
Traditional Search & Static Playbooks: Slow, fragmented across scattered documentation, and hard to correlate with real-time stack traces.

DevFix AI solves this by running precision DevOps troubleshooting over open-weight AI models (such as Meta's llama3.2:3b, Alibaba's qwen2.5-coder:7b, or Mistral) hosted locally or in your private VPC…

View on GitHub

Repository: https://github.com/MdFaisalDevops/DEvfix-Ai

License: MIT

How I Built It

DevFix AI is engineered as a clean, decoupled full-stack application built around open-weight models:

┌────────────────────────────────┐       ┌────────────────────────────────┐
│   Next.js 15 + Tailwind CSS    │       │     Python 3.12 + FastAPI      │
│  - Client-Side PII Redactor    │ ────> │  - Multi-Platform Classifier   │
│  - Interactive Sample Library  │ <──── │  - JSON Schema-Enforced Prompt │
│  - Local Browser Audit History │       │  - Fallback Heuristic Engine   │
└────────────────────────────────┘       └──────────────┬─────────────────┘
                                                        │
                                                        ▼
                                         ┌────────────────────────────────┐
                                         │         Ollama Runtime         │
                                         │  - Llama 3.2 (3B) / Qwen 2.5   │
                                         │  - Mistral (7B) / DeepSeek R1  │
                                         └────────────────────────────────┘

1. Open-Source AI Stack

AI Runtime: Ollama for local and private-VPC inference.
Primary Models:
- llama3.2:3b: Ultra-fast triage and root-cause summaries on standard laptops (~4GB RAM).
- qwen2.5-coder:7b: Deep code/script understanding for Kubernetes YAML, Dockerfiles, and Bash commands.
- mistral:7b: Robust reasoning across Linux systemd services and Terraform state conflicts.
Structured Schema Prompting: Uses Ollama's format: "json" mode with strict Pydantic schemas, ensuring the model never hallucinates fabricated commands or claims a fix was tested when it was not.

2. Frontend (Next.js 15 & Tailwind CSS v4)

Architecture: App Router, TypeScript, and Lucide icons with a dark developer aesthetic (#030712).
Client-Side Secret & PII Redactor: Pre-execution regex engine that strips AWS keys (AKIA...), database credentials (postgres://user:pass@...), personal access tokens (ghp_...), JWTs, and internal IPv4 addresses right in the browser before any network transmission.
Local Browser History: Persists analysis reports in localStorage with filtering, keyword search, and JSON export.

3. Backend & Orchestration (FastAPI & Docker Compose)

FastAPI (Python 3.12): Async endpoint pipeline (/api/analyze, /api/redact, /api/models/status, /api/samples, /api/feedback).
Docker Compose: Multi-service composition spinning up the frontend, backend, and optional bundled Ollama container with a single command: docker compose up --build.

Why Does Open Innovation Matter?

Open innovation is not just a philosophical preference for DevFix AI—it is the architectural foundation that makes the product viable:

Air-Gapped & Offline Reliability: When a core DNS provider or cloud WAN goes down, your troubleshooting assistant cannot depend on external SaaS connectivity. Open-weight models running on local hardware diagnose outages even during total internet blackouts.
Eliminating the "Data Exfiltration Tax": Many enterprise security teams ban cloud AI wrappers outright because logs contain proprietary intellectual property and credentials. Open-weight AI provides 100% compliance with zero third-party data egress.
Economics for High-Volume DevOps: Parsing a single 20,000-line crash dump through closed APIs costs real money on every run. Open weights deliver unlimited triage at $0 marginal token cost.
Reproducibility Without Vendor Drift: Closed APIs silently deprecate model versions and alter reasoning prompts. With open weights, you pin exact model hashes for consistent root-cause diagnosis.

My Agent Session

This application was architected, written, and verified using Google's Antigravity Advanced Agentic Coding environment. The agent autonomously scaffolded the Next.js 15 frontend and FastAPI backend, created the regex secret redaction rules, wrote and passed 10/10 Pytest unit tests, set up Docker Compose, verified the browser end-to-end with visual recordings, resolved .gitignore exclusion issues, and committed/pushed the code directly to GitHub.

My First User

During MVP testing, I shared DevFix AI with a DevOps engineer who was debugging a recurring CrashLoopBackOff on a payment microservice pod.

The Problem: The pod was intermittently terminating with Exit Code 137.
The Result: DevFix AI detected the OOMKilled signal, cited the cgroup limit disparity (512Mi limit vs. JVM heap allocation spikes), and generated the exact read-only verification command:

  kubectl describe pod <pod-name> -n production
  kubectl top pod <pod-name> -n production --containers

It recommended adjusting the memory limit to 1.5Gi and configuring JAVA_TOOL_OPTIONS='-XX:MaxRAMPercentage=75.0' with a rolling update rollback command.

User Feedback: "The fact that it masks credentials before analysis and warns you to review commands before running them in production makes it 10x more trustworthy than blindly pasting logs into ChatGPT."

Prize Categories

Primary Track: Side Hustle Challenge (Open-Source AI tools with viable developer product models)
Open-Weight AI: Local & private inference using Ollama, Llama 3, and Qwen 2.5 Coder

Devfix-Ai

Mohammed Faisal Bagban — Sun, 18 Oct 2026 14:25:12 +0000

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

🛠️ DevFix AI — Private DevOps Troubleshooting with Open-Weight AI

What I Built

Who Would Pay for It & What Problem Does It Solve?

Engineering teams face a high-stakes dilemma during production incidents:

The Closed Cloud AI Trap: Piping infrastructure logs into proprietary APIs (OpenAI, Claude) is dangerous. Logs contain sensitive organizational footprints: private IP subnets, database credentials, internal hostnames, and auth tokens. For regulated industries (healthcare, defense, fintech), this violates SOC 2, HIPAA, and GDPR. Furthermore, multi-thousand-line crash dumps incur unpredictable, high monthly token bills.
Traditional Playbooks: Searching documentation during a 2 AM outage is slow and disconnected from real-time stack traces.

DevFix AI solves this as a side-hustle product:

Zero Data Leakage: Powered by open-weight models (via Ollama) running locally on the engineer's machine or inside their private VPC.
Zero Per-Token Charges: Unlimited log diagnostics without recurring API invoices.
Enforced Safety: Commands are classified as Read-Only or Requires Sudo and strictly require human review before running—never auto-executing blindly in production.
Commercial Potential: A freemium self-hosted open-source core with proposed $19/seat team tiers offering shared remediation playbooks, Slack incident webhooks, and private team audit logs.

Demo

🌐 Live Web Application: https://d-evfix-ai-12ck-nu.vercel.app/
🔌 FastAPI Backend (Local/Docker): http://localhost:8000/docs

Note on Testing: The live Vercel app includes a built-in Deterministic Client Engine, allowing you to test real-world Kubernetes, Docker, Jenkins, Linux, Terraform, and AWS failures immediately out-of-the-box without configuring any API keys or local runtimes!

Code

MdFaisalDevops / DEvfix-Ai

🛠️ DevFix AI

AI-Powered DevOps & SRE Troubleshooting Assistant

Diagnose Infrastructure Errors with Open-Weight AI (Ollama) — 100% Private, Air-Gapped Ready & $0 Cloud Token Fees

🚀 Try the Live Web App on Vercel

Explore Features • Quickstart • Architecture • Supported Platforms • Deployment • Contributing

📌 Why DevFix AI?

Modern DevOps teams face a difficult dilemma during incidents:

Proprietary Cloud AI APIs (OpenAI, Claude): While smart, sending infrastructure logs to external APIs exposes sensitive internal hostnames, private IP subnets, database credentials, and trace IDs to third-party data centers. Furthermore, verbose multi-thousand-line crash logs result in unpredictable, exorbitant monthly token bills.
Traditional Search & Static Playbooks: Slow, fragmented across scattered documentation, and hard to correlate with real-time stack traces.

View on GitHub

Repository: https://github.com/MdFaisalDevops/DEvfix-Ai

License: MIT

How I Built It

DevFix AI is engineered as a clean, decoupled full-stack application built around open-weight models:

┌────────────────────────────────┐       ┌────────────────────────────────┐
│   Next.js 15 + Tailwind CSS    │       │     Python 3.12 + FastAPI      │
│  - Client-Side PII Redactor    │ ────> │  - Multi-Platform Classifier   │
│  - Interactive Sample Library  │ <──── │  - JSON Schema-Enforced Prompt │
│  - Local Browser Audit History │       │  - Fallback Heuristic Engine   │
└────────────────────────────────┘       └──────────────┬─────────────────┘
                                                        │
                                                        ▼
                                         ┌────────────────────────────────┐
                                         │         Ollama Runtime         │
                                         │  - Llama 3.2 (3B) / Qwen 2.5   │
                                         │  - Mistral (7B) / DeepSeek R1  │
                                         └────────────────────────────────┘

1. Open-Source AI Stack

AI Runtime: Ollama for local and private-VPC inference.
Primary Models:
- llama3.2:3b: Ultra-fast triage and root-cause summaries on standard laptops (~4GB RAM).
- qwen2.5-coder:7b: Deep code/script understanding for Kubernetes YAML, Dockerfiles, and Bash commands.
- mistral:7b: Robust reasoning across Linux systemd services and Terraform state conflicts.
Structured Schema Prompting: Uses Ollama's format: "json" mode with strict Pydantic schemas, ensuring the model never hallucinates fabricated commands or claims a fix was tested when it was not.

2. Frontend (Next.js 15 & Tailwind CSS v4)

Architecture: App Router, TypeScript, and Lucide icons with a dark developer aesthetic (#030712).
Client-Side Secret & PII Redactor: Pre-execution regex engine that strips AWS keys (AKIA...), database credentials (postgres://user:pass@...), personal access tokens (ghp_...), JWTs, and internal IPv4 addresses right in the browser before any network transmission.
Local Browser History: Persists analysis reports in localStorage with filtering, keyword search, and JSON export.

3. Backend & Orchestration (FastAPI & Docker Compose)

FastAPI (Python 3.12): Async endpoint pipeline (/api/analyze, /api/redact, /api/models/status, /api/samples, /api/feedback).
Docker Compose: Multi-service composition spinning up the frontend, backend, and optional bundled Ollama container with a single command: docker compose up --build.

Why Does Open Innovation Matter?

Open innovation is not just a philosophical preference for DevFix AI—it is the architectural foundation that makes the product viable:

Air-Gapped & Offline Reliability: When a core DNS provider or cloud WAN goes down, your troubleshooting assistant cannot depend on external SaaS connectivity. Open-weight models running on local hardware diagnose outages even during total internet blackouts.
Eliminating the "Data Exfiltration Tax": Many enterprise security teams ban cloud AI wrappers outright because logs contain proprietary intellectual property and credentials. Open-weight AI provides 100% compliance with zero third-party data egress.
Economics for High-Volume DevOps: Parsing a single 20,000-line crash dump through closed APIs costs real money on every run. Open weights deliver unlimited triage at $0 marginal token cost.
Reproducibility Without Vendor Drift: Closed APIs silently deprecate model versions and alter reasoning prompts. With open weights, you pin exact model hashes for consistent root-cause diagnosis.

My Agent Session

My First User

During MVP testing, I shared DevFix AI with a DevOps engineer who was debugging a recurring CrashLoopBackOff on a payment microservice pod.

The Problem: The pod was intermittently terminating with Exit Code 137.
The Result: DevFix AI detected the OOMKilled signal, cited the cgroup limit disparity (512Mi limit vs. JVM heap allocation spikes), and generated the exact read-only verification command:

  kubectl describe pod <pod-name> -n production
  kubectl top pod <pod-name> -n production --containers

It recommended adjusting the memory limit to 1.5Gi and configuring JAVA_TOOL_OPTIONS='-XX:MaxRAMPercentage=75.0' with a rolling update rollback command.

User Feedback: "The fact that it masks credentials before analysis and warns you to review commands before running them in production makes it 10x more trustworthy than blindly pasting logs into ChatGPT."

Prize Categories

Primary Track: Side Hustle Challenge (Open-Source AI tools with viable developer product models)
Open-Weight AI: Local & private inference using Ollama, Llama 3, and Qwen 2.5 Coder

WildWhisper AI 🌿 An Offline-First Pocket Nature Guide (Powered by Gemini)

Mohammed Faisal Bagban — Wed, 07 Oct 2026 20:44:37 +0000

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

What I Built

WildWhisper AI is an offline-first, gamified nature companion designed with one core philosophy: AI should reduce screen time, not increase it.

Most AI apps today demand your constant visual attention, trapping you in chat interfaces or dashboards. WildWhisper flips this paradigm by acting as your pocket-sized nature guide. It encourages users—especially tech-addicted individuals and young explorers—to get outside, listen, and observe.

Here is how it works:

Audio & Vision Identification: Users can record bird calls or take photos of plants/insects to instantly identify them via AI.
Whisper Mode: Once a mission is generated, the app instructs you to lock your screen and put the phone in your pocket. Using the Web Speech API and Haptic feedback, it periodically "whispers" instructions (e.g., "Walk quietly for 2 minutes and listen for rustling leaves") without requiring you to look at the screen.
Mystery Sounds & Gamification: A built-in discovery journal and offline badge system reward actual physical exploration over endless scrolling.

Demo

🌿 Live Application: wildwhisper-ai.vercel.app

(Note: WildWhisper features a "Bring Your Own Key" architecture. To use live Gemini AI inference instead of the built-in offline Demo mode, click the Profile icon and enter your free Gemini API Key!)

Code

MdFaisalDevops / Wildwhisper-Ai

This is my hacktoberfest weekend challenge 2

🌿 WildWhisper AI

Listen. Look. Discover.

🌿 Live Application: wildwhisper-ai.vercel.app

WildWhisper is an offline-first AI nature companion that helps users identify birds and nature, then encourages them to physically explore the outdoors. Built for the Touch Grass hackathon theme.

The core philosophy of WildWhisper AI is: AI should reduce screen time, not increase it.

🌟 Features

Audio Bird Identification: Use your microphone to listen to bird calls. The AI analyzes the audio and identifies the species, returning rich data, images, and sample sounds.
Nature Camera: Point your camera at a plant, tree, or insect to identify it instantly.
Whisper Mode: An immersive, screen-darkening mode that guides you through outdoor missions using Haptic feedback and Voice Guidance, encouraging you to put your phone in your pocket.
AI Mission Explorer: Generates dynamic, contextual outdoor missions based on your time available, desired activity, and difficulty.
Mystery Sound Game…

View on GitHub

How I Built It

WildWhisper was built for absolute resilience and speed using a modern web stack:

Framework: Next.js 16 (App Router) combined with Tailwind CSS for glassmorphism aesthetics.
Local-First Storage: I used idb-keyval (IndexedDB) to ensure the Discovery Journal and Badges work perfectly without an internet connection.
AI Integration (Google Gemini): For real-time inference, I integrated the @google/generative-ai SDK using gemini-1.5-flash. The AI powers three core components:
1. Vision AI: Analyzes camera frames to identify local flora and fauna.
2. Audio AI: Analyzes recorded nature sounds (birds, frogs) to classify the species.
3. Mission Generator: An LLM agent that takes the user's available time and desired difficulty to generate hyper-contextual outdoor "missions" (e.g., "Find a leaf that has fallen recently").
Web APIs: Utilized MediaRecorder for audio capture, react-webcam for vision capture, and the SpeechSynthesis API for screen-free guidance.

Why Does Open Innovation Matter?

Open innovation is the backbone of this project. Building a local-first, privacy-respecting app requires architecture where the user controls their data. By designing a system that can eventually drop in open-weight models (like Transformers.js running locally in the browser) or allow users to bring their own API keys (BYOK), we remove the dependency on centralized, closed, and paid APIs.

In the context of the "Touch Grass" theme, open innovation means giving users the tools to explore nature without being tracked, monitored, or monetized by large corporations.

My Agent Session

This project was built iteratively with the help of Google's Antigravity AI coding agent. The agent handled bootstrapping the complex UI components, implementing the IndexedDB persistence layer, and wiring up the hybrid AI providers seamlessly.

Prize Categories

Google AI: For deep integration of the Gemini 1.5 Flash model for multi-modal (Audio/Vision) identification and dynamic text generation (Missions).

StudySprint

Mohammed Faisal Bagban — Sun, 04 Oct 2026 14:56:37 +0000

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

What I Built

I built StudySprint, a collaborative study planner web application designed specifically for a friend who is currently tackling a heavy load of university coursework. They often struggled with managing deadlines across different subjects and lacked a unified system to practice active recall while managing their time.

StudySprint solves this by integrating:

A dynamic Subjects & Tasks Manager to keep track of upcoming exams and assignments.
A built-in Pomodoro Timer with "Focus", "Short Break", and "Long Break" modes that automatically tracks daily streaks.
A Progress Dashboard showing completed tasks vs. daily goals.
AI Study Partner (The cool addition!): An AI-driven feature that generates custom study schedules based on upcoming exam deadlines and automatically creates interactive 3D flashcards to help with active recall.

Demo

🔗 Live Demo of StudySprint

Code

MdFaisalDevops / Hacktoberfest-challenge-1

This is my hacktoberfest weekend challenge 1

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

What I Built

StudySprint solves this by integrating:

A dynamic Subjects & Tasks Manager to keep track of upcoming exams and assignments.
A built-in Pomodoro Timer with "Focus", "Short Break", and "Long Break" modes that automatically tracks daily streaks.
A Progress Dashboard showing completed tasks vs. daily goals.
AI Study Partner (The cool addition!): An AI-driven feature that generates custom study schedules based on upcoming exam deadlines and automatically creates interactive 3D flashcards to help with active recall.

Demo

🔗 Live Demo of StudySprint (Currently running locally. See repo…

View on GitHub

How I Built It

I built this project utilizing a modern frontend stack: React, Vite, and vanilla CSS (focusing on a premium dark mode, glassmorphic UI).

To rapidly develop the UI, components, and the simulated AI features, I collaborated with an Agentic AI Coding Assistant (Antigravity). The AI agent harness allowed me to rapidly iterate on the frontend design by orchestrating complex CSS layouts and React state management autonomously. We designed an "AI Study Plan" feature which parses the user's upcoming exams to simulate how an open-weights LLM could ingest upcoming tasks and output both a prioritized schedule and an interactive flashcard deck for active recall.

Why Does Open Innovation Matter?

Open innovation was crucial for this project because it allows developers to build hyper-localized, personalized tools for their loved ones without being locked into expensive, rigid, or closed productivity ecosystems. By leveraging open-source tools (like React, Vite, and Lucide icons) and open AI frameworks, I was able to rapidly craft a premium-feeling educational tool that perfectly fit my friend's unique studying habits. It proves that with open innovation, anyone can build powerful, custom solutions for the people they care about.

My Agent Session

[Link to my Agent Session]

Prize Categories

Maintainer/Contributor categories
AI/Developer Tooling

Intro

Mohammed Faisal Bagban — Fri, 02 Oct 2026 19:02:30 +0000

I am new to the community.
Happy to be part of dev.

Hello

Mohammed Faisal Bagban — Fri, 02 Oct 2026 19:00:10 +0000

DEV Community: Mohammed Faisal Bagban

Lazylist-AI

What I Built

The Problem

The Solution: "Do less. Stress less. 🦥"

Demo

Code

MdFaisalDevops / slow-and-steady

🦥 LazyList AI

Your tasks. Less stress.

📖 Table of Contents

🌿 Overview & Philosophy

How I Built It

1. Genuine Open-Weight AI (qwen2.5:0.5b)

2. Transparent Dual-Engine Architecture

3. Tranquil Design System

Why Does Open Innovation Matter?

My Agent Session

The Lazy Payoff

Prize Categories

DEV-fix-AI

🛠️ DevFix AI — Private DevOps Troubleshooting with Open-Weight AI

What I Built

Who Would Pay for It & What Problem Does It Solve?

Demo

Code

MdFaisalDevops / DEvfix-Ai

🛠️ DevFix AI

AI-Powered DevOps & SRE Troubleshooting Assistant

Diagnose Infrastructure Errors with Open-Weight AI (Ollama) — 100% Private, Air-Gapped Ready & $0 Cloud Token Fees

📌 Why DevFix AI?

How I Built It

1. Open-Source AI Stack

2. Frontend (Next.js 15 & Tailwind CSS v4)

3. Backend & Orchestration (FastAPI & Docker Compose)

Why Does Open Innovation Matter?

My Agent Session

My First User

Prize Categories

Devfix-Ai

🛠️ DevFix AI — Private DevOps Troubleshooting with Open-Weight AI

What I Built

Who Would Pay for It & What Problem Does It Solve?

Demo

Code

MdFaisalDevops / DEvfix-Ai

🛠️ DevFix AI

AI-Powered DevOps & SRE Troubleshooting Assistant

Diagnose Infrastructure Errors with Open-Weight AI (Ollama) — 100% Private, Air-Gapped Ready & $0 Cloud Token Fees

📌 Why DevFix AI?

How I Built It

1. Open-Source AI Stack

2. Frontend (Next.js 15 & Tailwind CSS v4)

3. Backend & Orchestration (FastAPI & Docker Compose)

Why Does Open Innovation Matter?

My Agent Session

My First User

Prize Categories

WildWhisper AI 🌿 An Offline-First Pocket Nature Guide (Powered by Gemini)

What I Built

Demo

Code

MdFaisalDevops / Wildwhisper-Ai

This is my hacktoberfest weekend challenge 2

🌿 WildWhisper AI

🌟 Features

How I Built It

Why Does Open Innovation Matter?

My Agent Session

Prize Categories

StudySprint

What I Built

Demo

Code

MdFaisalDevops / Hacktoberfest-challenge-1

This is my hacktoberfest weekend challenge 1

What I Built

Demo

How I Built It

Why Does Open Innovation Matter?

1. Genuine Open-Weight AI (`qwen2.5:0.5b`)