DEV Community: HMV

GentleBrief: Anti-Doomscroll Daily Audio Digests Powered by Open-Weight AI

HMV — Tue, 20 Oct 2026 16:38:40 +0000

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

What I Built

Modern web browsing often feels like cognitive overload. Checking the morning news across Hacker News, tech blogs, and research hubs frequently pulls readers into endless doomscrolling—fighting clickbait headlines, sensationalist takes, cookie banners, tracking scripts, and algorithmic rage-bait.

GentleBrief acts as a mindful anti-doomscroll barrier.

Instead of opening 40 tabs and exhausting your mental bandwidth before breakfast, GentleBrief automates the morning check-in:

You pick the desks that matter to you (or drop in any public blog/RSS link).
It quietly sends a cloud browser to extract the articles behind the scenes.
An open-weight model strips away the hysteria, point tallies, and clickbait, distilling the developments into three calm, grounded facts.
It narrates the digest into a conversational, ambient audio briefing that you can listen to hands-free while getting ready, walking, or drinking your morning coffee.

It lets developers and knowledge workers be intentionally "lazy" about consuming information—staying fully informed without ever getting sucked into a screen.

Demo

Live Application: gentle-brief.onrender.com
Features in action:
Automated cloud extraction bypassing tracking scripts and popups.
Custom calm-pacing voice narration with soothing ambient soundscapes.
Per-user client-side isolated playback history.
Live anti-doomscroll metrics highlighting filtered headlines and minutes of screen time saved.

Code

AmjustGettingStarted / Gentle-Brief

Gentle Brief

Gentle Brief is a Next.js app for turning a curated set of sources into a polished daily brief. It reads the latest input from selected feeds, distills the signal, and presents a readable summary with pacing and voice controls.

What it does

Selects and combines topic sources from built-in and custom URLs
Brews a short digest from those sources
Supports a pacing menu and voice ambience settings
Keeps a history of generated digests for replay
Uses a browser-based or live pipeline depending on configuration

Tech stack

Next.js 16
React 19
TypeScript
Tailwind CSS
Sonner for toast notifications

Getting started

Install dependencies:
```
npm install
```
Start the development server:
```
npm run dev
```
Open the app in your browser:
```
http://localhost:3000
```

Available scripts

npm run dev
npm run build
npm run start
npm run lint

Project notes

This project is a front-end digest dashboard with a generated brief workflow. The main app…

View on GitHub

Built with:

Framework: Next.js (App Router, TypeScript)
Styling & UI: Tailwind CSS, Radix UI, shadcn/ui
Cloud Scraping: Browserbase SDK
Inference Engine: Groq API running open-weight Meta Llama 3 / Google Gemma
Audio Synthesis: ElevenLabs Conversational Voice API

How I Built It

The pipeline is built around an open-weight inference architecture orchestrated through Next.js:

Headless Extraction (Browserbase): Rather than fragile client fetches that fail against bot walls and modern SPAs, GentleBrief spins up headless cloud browser sessions via Browserbase. It navigates to configured desks (e.g., Hacker News, Indie Hackers, AP News, Phys.org) and scrapes strictly semantic article content, intentionally discarding navbars, paywall banners, and ad clutter.
Open-Weight Distillation (Llama 3 / Gemma on Groq): The raw scrape payload is routed to open-weight LLMs via Groq. The system prompt is fine-tuned to function as a stoic, mindful editor. It is explicitly instructed to eliminate hype, ignore upvote/comment counts, reject fear-mongering framing, and synthesize the day's core signals into peaceful, clear sentences formatted for vocal narration.
Ambient Voice Narration (ElevenLabs): The distilled script is sent to the ElevenLabs API using voice profiles like Charlotte (soft, gentle) or Adam (calm, conversational). The generated audio stream is fed to the dashboard player with custom scrubbing, speed controls, and optional ambient sound layers.

Why Does Open Innovation Matter?

Open-source and open-weight AI (like Llama 3 and Gemma) are essential for personal software like GentleBrief.

Information filtering is inherently subjective. When news curation is locked behind closed, proprietary platforms, users are held hostage by engagement algorithms designed to provoke anxiety and maximize screen time. Open models give developers full control over the editorial ethos: we can inspect the prompts, enforce complete neutrality, self-host or change inference providers at will, and guarantee that our tools serve human mental well-being rather than advertising metrics.

Open innovation makes calm technology accessible without closed-ecosystem gatekeeping.

The Lazy Payoff

GentleBrief replaced a fragmented morning habit:

Before: 30–45 minutes bouncing across Hacker News, Twitter, and tech sites, leaving multiple tabs open and feeling mentally scattered before work.
With GentleBrief: 0 minutes of doomscrolling. Clicking Brew Digest runs the cloud pipeline in seconds, producing a 60-to-90-second audio recap with three clear bullet points.
Estimated impact: Saves roughly ~25 minutes of screen fatigue every single morning.

Prize Categories

Best Use of ElevenLabs: Dynamic voice synthesis generating tranquil, ambient audio dispatches.
Best Use of Browserbase: Headless cloud browsing automating the extraction of public news feeds and custom URLs without ads or tracking.

Ghost Scout | Privacy-First AI Job Matcher for Tech Professionals

HMV — Tue, 13 Oct 2026 19:11:31 +0000

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

What I Built

GhostScout is a privacy-focused, high-end job matching web tool designed for developers and tech professionals who want AI-powered resume analysis and recruiter outreach drafting without vendor lock-in.

The Problem It Solves: Traditional job boards and AI resume matchers force users to upload sensitive career history and personal data into black-box, closed ecosystems. GhostScout gives users full control by utilizing open-weight models for precise resume-to-job scoring and customized outreach generation.
Who Pays for It? Active job seekers, freelancers, and tech professionals who want an edge in their job search while maintaining data sovereignty. It features a freemium model offering 3 free scans, followed by a $9/month "Pro Scout" subscription via Stripe.

Demo

Live App: ghostscout.thehmv.tech

Code

GitHub Repository: AmjustGettingStarted/Job-Scout

How I Built It

GhostScout is built for speed, responsiveness, and a distinct visual identity:

Frontend & UI: Next.js (App Router), Tailwind CSS, Shadcn UI primitives, Framer Motion for animations, and Lenis for smooth momentum scrolling.
Aesthetic: A clean, paper-sculpted design system with origami-inspired geometric accents, stark typography, dynamic pill badges, and a coral-and-sand palette (#ff6b6b, #f4a261).
AI Backend: Dual-mode inference supporting local open-weight models via Ollama or hosted inference via the Tinker API for private resume scoring and outreach email drafting.
Monetization: Stripe Checkout integration (Test Mode) handling secure $9/month recurring subscriptions.
Infrastructure: Deployed as a dynamic Web Service on Render with custom domain DNS routing through get.tech and automated SSL certification.

Why Does Open Innovation Matter?

Open-weight models (run locally via Ollama or transparently via Tinker) make true data privacy possible, letting users keep absolute ownership of their career footprint.

Prize Categories

Main Challenge: Side Hustle (Hacktoberfest Open-Source AI Challenge Week 2)
Partner Categories:
- Best Use of Render: App hosted live as a dynamic Web Service on Render.
- Best Use of Tinker: Powered by Tinker API for hosted open-weight inference.
- Best Use of a .tech Domain: Deployed live on ghostscout.thehmv.tech.

GhostScout | Privacy-First AI Job Matcher for Tech Professionals

HMV — Tue, 13 Oct 2026 18:57:40 +0000

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

What I Built

GhostScout is a privacy-focused, high-end job matching web tool designed for developers and tech professionals who want AI-powered resume analysis and recruiter outreach drafting without vendor lock-in.

The Problem It Solves: Traditional job boards and AI resume matchers force users to upload sensitive career history and personal data into black-box, closed ecosystems. GhostScout gives users full control by utilizing open-weight models for precise resume-to-job scoring and customized outreach generation.

Who Pays for It? Active job seekers, freelancers, and tech professionals who want an edge in their job search while maintaining data sovereignty. It features a freemium model offering 3 free scans, followed by a $9/month "Pro Scout" subscription via Stripe.

Demo

Live App: https://ghostscout.thehmv.tech

Code

GitHub Repository: https://github.com/AmjustGettingStarted/Job-Scout

How I Built It

GhostScout is built for speed, responsiveness, and a cinematic aesthetic:

Frontend & UI: Next.js (App Router), Tailwind CSS, Shadcn UI primitives, Framer Motion for animations, and Lenis for smooth momentum scrolling.
Aesthetic: A clean, paper-sculpted design system with origami-inspired geometric accents, stark typography, dynamic pill badges, and a coral-and-sand palette (#ff6b6b, #f4a261)
AI Backend: Dual-mode inference supporting local open-weight models via Ollama or hosted inference via the Tinker API for private resume scoring and outreach email drafting.
Monetization: Stripe Checkout integration (Test Mode) handling secure $9/month recurring subscriptions.
Infrastructure: Deployed as a dynamic Web Service on Render with custom domain DNS routing through get.tech and automated SSL certification.

Why Does Open Innovation Matter?

Open innovation is critical for tools that process deeply personal data like resumes, career histories, and salary expectations. Relying on closed, proprietary APIs means handing over private professional data to third-party black boxes with opaque data retention policies. Open-weight models (run locally via Ollama or transparently via Tinker) make true data privacy possible, letting users keep absolute ownership of their career footprint.

Prize Categories

Main Challenge: Side Hustle (Hacktoberfest Open-Source AI Challenge Week 2)
Partner Categories:
- Best Use of Render: App hosted live as a dynamic Web Service on Render.
- Best Use of Tinker: Powered by Tinker API for hosted open-weight inference.
- Best Use of a .tech Domain: Deployed live on ghostscout.thehmv.tech.

Touch Grass to Deploy: The Git Hook That Refuses to Push Until You Go Outside

HMV — Tue, 06 Oct 2026 16:27:11 +0000

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

What I Built

Touch Grass to Deploy is an automated Git pre-push gatekeeper powered by a local, open-weight vision-language model (moondream2).

As developers, we pride ourselves on relentless productivity, rapid git pushes, and shipping code. But that loop often keeps us chained to our monitors for hours without taking a genuine physical break. Switching tabs to a browser or checking a phone isn't a break—it's just swapping one screen for another.

This tool enforces a literal physical boundary: your code will refuse to deploy until you physically step away from your desk, walk outside, and provide authentic photographic evidence of nature.

When you run git push, the hook halts execution in the terminal. It inspects your project root for proof of nature (grass.jpg) and runs local vision inference. If it verifies real foliage, grass, trees, or sky, the push is authorized, the image is consumed, and your code deploys. If you haven't stepped outside—or tried to trick it with indoor monitor screenshots or terminal text—the deployment is immediately aborted.

Demo

1. The Blocked State (No outdoor proof found)

$ git push origin main

======================================================================
  🌿 TOUCH GRASS TO DEPLOY | Git Pre-Push Gatekeeper 🌿
======================================================================

🚫 DEPLOYMENT BLOCKED: NO PROOF OF NATURE FOUND!
----------------------------------------------------------------------
You have attempted to `git push` without providing physical evidence
that you have stepped away from your screen.

👉 HOW TO UNLOCK YOUR GIT PUSH:
  1. Stand up from your desk.
  2. Walk outside into the physical world.
  3. Touch real grass, foliage, or gaze at the sky.
  4. Snap a photo on your phone.
  5. Save the photo as grass.jpg in your project root.
  6. Re-run `git push`.

"The screen should be the shortest part of the experience."
----------------------------------------------------------------------

❌ git push aborted by Touch Grass gatekeeper.
error: failed to push some refs

2. The Verification Passed State (After touching real grass)

$ git push origin main

======================================================================
  🌿 TOUCH GRASS TO DEPLOY | Git Pre-Push Gatekeeper 🌿
======================================================================
Found candidate proof: grass.jpg

[1/3] 📷 Inspecting proof: grass.jpg...
[2/3] 🧠 Initializing local vision model (vikhyatk/moondream2 on CPU)...
      (Zero cloud API calls. Complete offline privacy.)
[3/3] 🔍 Analyzing visual features for authentic outdoor nature...
      AI Model Verdict: YES

✅ PROOF ACCEPTED! NATURE CONFIRMED.
----------------------------------------------------------------------
🌿 Congratulations! You touched grass and disconnected from the matrix.
🚀 Your git push has been authorized by local vision intelligence.

🧹 Consumed grass.jpg (fresh proof required for future pushes).

Proceeding with remote deployment...
Everything up-to-date

Code

AmjustGettingStarted / touch-grass-to-deploy

touch-grass-to-deploy

View on GitHub

The project is structured with zero bloat:

verify_grass.py: The local vision pipeline loading moondream2 and querying the model for outdoor flora.
setup_hook.py: Automated setup script to configure the Git hook either per-repository or globally across every repo on your computer.
.git/hooks/pre-push: Native shell hook intercepting the push signal.

How I Built It

The core design principle was ensuring that the screen is the shortest part of the experience, and that anyone even on a low-spec laptop can run this without expensive cloud infrastructure.

Native Git Interception: Built using Git's native pre-push client hook system. It intercepts the push lifecycle before any network packets leave the machine.
Open-Weight Vision AI (moondream2): Rather than calling proprietary multimodal APIs, I used vikhyatk/moondream2 (revision 2024-08-26), a compact ~1.86B parameter vision model.
Pure CPU Execution: Configured using PyTorch CPU wheels with low_cpu_mem_usage=True and evaluated inside torch.no_grad(). It requires no dedicated GPU and runs seamlessly within standard RAM constraints.
Single-Use Verification Mechanism: When an outdoor photo is verified (YES), the script deletes grass.jpg from the folder. This ensures you can't reuse the same leaf photo for your next feature push—you have to get outside again.

Why Does Open Innovation Matter?

This project could not function ethically or practically with closed-source, proprietary APIs:

100% Offline Capability (Works in Nature): If you are coding from a park, a trail, or a spot with zero cellular coverage, a closed API like GPT-4o or Claude is completely useless. Because moondream2 runs locally via open weights, git verification works entirely off-grid with zero internet connection.
Zero Cost Barrier: Developers push code dozens of times a day. Tying each push to a pay-per-token commercial API would rack up bills and hit rate limits. Open weights allow you to verify unlimited deployments for $0.00 forever.
Absolute Privacy of Personal Photos: Your phone photos contain sensitive EXIF metadata, GPS coordinates, and glimpses of your personal surroundings. With open-weight AI executing directly in local memory, zero pixels and zero bytes of location telemetry ever leave your machine.

Prize Categories

Hacktoberfest Week 1: Touch Grass
Hugging Face Open-Source AI Challenge

CareCue AI | Transforming Messy Prescriptions into Timely Reminders for Loved Ones

HMV — Fri, 02 Oct 2026 14:06:54 +0000

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

What I Built

I built CareCue AI, an accessible, privacy-centric medication schedule companion designed for family caregivers and loved ones who manage multiple daily prescriptions.

My grandfather spends most weekdays home alone while my parents are at work and I am out for classes. Keeping track of his daily medications was a persistent challenge. Messy prescription notes with conflicting meal timings (e.g., "twice daily with meals") are hard to parse, and typical smartphone alarm apps are frustrating for him to configure. We spent too much time worrying about missed doses from afar, which made building a dead-simple, empathetic reminder companion a top priority

CareCue AI solves this through a straightforward flow:

Unstructured Prescription Ingestion: Caregivers paste or type rough doctor instructions directly into the interface.
AI Schedule Extraction: An open-weight AI model parses the notes into structured records, cleans up conversational filler, and splits multi-intake frequencies (such as morning, lunch, and dinner doses) into distinct timetable entries.
Editable Verification: Before committing to a schedule, users review the structured cards, adjust times or dosages if needed, and save them with one click.
Accessible Audio-Visual Alerts: When a dose is due, CareCue AI sounds a browser chime using the native Web Audio API and presents a high-contrast alert modal complete with an empathetic reminder cue, snooze option, and a one-click "Mark as Taken" action.

Demo

Live Application: https://carecue-ai-yquo.onrender.com

Code

AmjustGettingStarted / carecue-ai

A smart, privacy-first medicine reminder that turns messy prescriptions into timely audio alerts and structured schedules for family members, powered by open-source AI.

CareCue AI

Accessible, Privacy-Centric Medicine Reminder & Caregiver Dashboard
Built with Next.js (App Router, TypeScript), Tailwind CSS, and shadcn/ui.
Hacktoberfest Challenge 1 Compliant: Powered by Open-Source AI (Llama 3.1 / Gemma 2).

🌟 Overview & Key Features

CareCue AI bridges the gap between messy medical prescriptions and reliable medication adherence:

Intelligent Ingestion via Open-Source AI:
- Parses unstructured doctor notes, discharge summaries, or caregiver instructions.
- Extracts exact drug names, dosages, 24-hour schedules (HH:MM), and dietary constraints.
- Synthesizes an empathetic, warm, easy-to-read one-sentence reminder prompt (friendlyCue) tailored for family members or elderly relatives.
- Pre-loaded with three quick-sample presets
  - Dad's Blood Pressure & Sugar
  - Post-Surgery Recovery
  - Grandma's Evening Routine
Zero-Cloud Client Privacy & LocalStorage Persistence:
- Stores schedules, dose logs, and timestamps locally in the browser.
- Zero mandatory database setup — runs instantly on any device.
In-Browser Web Audio API Chime & High-Contrast Alarms:
- Synthesized melodic…

View on GitHub

How I Built It

The application is built using modern web standards and open-source tooling:

Framework: Next.js (App Router, TypeScript)
Styling & UI: Tailwind CSS and accessible component patterns inspired by shadcn/ui
Open-Source AI Backend: Powered by an open-weight instruction-tuned model (Llama 3.1 8B Instruct) queried via an OpenAI-compatible inference endpoint.
Sanitization & Splitting Pipeline: Implemented a dedicated post-processing module (lib/prescriptionSanitizer.ts) using regular expressions and time-slot mapping. This ensures medication names are clean of conversational glue words (like "take" or "and one") and automatically expands bundled frequencies into individual, scheduled daily events.
Audio Engine: Developed a client-side chime generator via the browser's native AudioContext (HTML5 Web Audio API), producing clear sound alerts without depending on external media assets or heavy libraries.
Hosting: Deployed on Render as a Node web service.

Why Does Open Innovation Matter?

Prescription habits, dosages, and medical timing data are deeply personal health details. Relying on closed, proprietary AI platforms introduces significant trade-offs: data can be logged to corporate telemetry pipelines, subject to vendor price shifts, or hidden behind black-box terms of service.

Open innovation and open-weight models fundamentally shift control back to the user:

Data Sovereignty & Health Privacy: Open-weight models like Llama allow healthcare-adjacent tools to run without funneling sensitive family routines into centralized corporate training silos.
Self-Hostable Resilience: The exact same inference pipeline can be run locally using Ollama or embedded into self-hosted home servers without ongoing subscription barriers.
Predictable, Long-Term Tooling: Open models empower independent developers to create vital accessibility tools for friends and relatives that remain dependable over time, free from arbitrary deprecations or forced API schema updates.

Prize Categories

Best Use of Render: The application is fully deployed and actively serving web requests as a Next.js service on Render.