DEV Community: Athul

An automated assistant that fills out online job application forms for you.

Athul — Sun, 25 Oct 2026 14:09:40 +0000

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

What I Built

What it does: It is an automated assistant that fills out online job application forms for you.

The problem it solves: Applying to jobs takes hours of typing the same information (name, experience, summary) over and over. This tool automates the boring typing part.

Who benefits: Job seekers who want to save time and energy during repetitive application processes.

Demo

How to see it in action: Clone the repo, set your profile in .env, and run python agent.py .

Visual confirmation: The browser opens automatically (headless=false), types the answers live on your screen, and takes screenshots before and after submitting.

Code

42lv88 / Job_Apply_Agent-

Apply for job using agent

Job Apply Agent 🤖

An autonomous job application agent that combines Playwright (browser automation) with Ollama/Gemma (local LLM) to automatically fill and submit job application forms.

Architecture

┌─────────────────────────────────────────────────┐
│                  agent.py (orchestrator)         │
└────┬───────────┬──────────────┬─────────────────┘
     │           │              │
     ▼           ▼              ▼
scraper.py  llm_client.py  form_filler.py
(Playwright) (Ollama HTTP)  (Playwright)
     │           │              │
     ▼           ▼              ▼
 Job page     Gemma 2B      Fill fields
 HTML/DOM     local LLM     + submit

Project Structure

Job_Apply_Agent-/
├── agent.py           # Main orchestrator – run this
├── config.py          # Env-var configuration loader
├── scraper.py         # Playwright scraper (JD + form fields)
├── llm_client.py      # Ollama HTTP client (Gemma)
├── prompt_builder.py  # Builds LLM prompt, parses JSON response
├── form_filler.py     # Fills fields + clicks Submit
├── test_pipeline.py   # Integration test with mock HTML page
├── requirements.txt
├── setup.sh
└── .env.example

Quick Start

1. Install dependencies

bash setup.sh

2. Configure your profile

cp .env.example .env
# Edit .env with your name, email, resume

…

View on GitHub

How I Built It

Core files breakdown:
agent.py: The main controller that connects everything together.
scraper.py: Looks at the webpage and finds all the text boxes and questions using Playwright.
llm_client.py: Talks to your local AI (Gemma) to figure out the best answers based on your resume.
form_filler.py: Types the answers into the form and clicks submit.

Playwright: A browser automation tool that acts like a robot hand, clicking buttons and typing into fields on web pages.

Ollama & Gemma 2B: A lightweight, open-weight AI model running locally on your computer. It reads the job description and form questions, then generates custom answers based on your profile.

Python Architecture: Built in modular pieces so the scraper, AI client, and form filler operate independently.

Why Does Open Innovation Matter?

Privacy first: Your resume, phone number, and personal details stay on your own computer instead of being sent to a third-party cloud server.

No API costs: Running an open-source model locally via Ollama means you don't pay subscription fees or per-token API costs.

Total control: You can modify the code, swap out models, or adjust safety flags (DRY_RUN=true) easily without depending on closed platform rules.

The Lazy Payoff

Time saved: Instead of spending 5 to 10 minutes filling out every single job form manually, the agent fills it out in seconds.

Safety net: With DRY_RUN=true and non-headless mode, you always stay in control to review the answers before anything gets submitted.

Simple Street Sign Treasure Hunt: Solve the riddle, go out,touch grass,take a photo and upload.

Athul — Sat, 10 Oct 2026 14:06:46 +0000

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

What I Built

Street Hunt: Offline AI Edition is a GPS-based web game that turns your neighborhood into a treasure hunt. Open it on your computer and it picks a real street a few hundred meters from where you're standing. It then gives you a Harry Potter-style riddle whose answer is that street's name.Go find the street sign board, and upload it on the site, it gives you a point and puts you on the leaderboard

You put the phone in your pocket, walk to the street, find the street sign, and take a photo of it. The app reads the photo and checks that it matches the street in the riddle. The game only works if you go outside, because the only way to win is to be standing in front of a real sign.

It's for anyone who wants a reason to explore their own area: families with kids, fantasy fans, and people who've lived somewhere for years without ever walking down half its streets.

Demo

Code

42lv88 / SimpleTreasureHuntMap

Simple Treasure Hunt of Map Locations

🗺️ Street Hunt: Offline AI Edition

A GPS-based mobile web game where you explore the real world to find dynamically generated street quests. This version is completely free and offline-first, powered by a local FastAPI backend using Ollama (Gemma) to generate Harry Potter-style riddles, and Tesseract OCR to verify the photos you take of street signs!

🏗️ Architecture

Frontend: Svelte + Vite + Leaflet (Map)
Backend: Python + FastAPI
AI Riddles: Local Ollama running a Gemma model
Sign Verification: Local Tesseract OCR

📋 Prerequisites

Before running the app, ensure you have the following installed on your Linux machine:

Node.js & npm (for the frontend)
Python 3.10+ (for the backend)
Tesseract OCR (System library for reading images)
- Fedora: sudo dnf install tesseract
- Ubuntu/Debian: sudo apt-get install tesseract-ocr
Ollama (for local AI)
- Install from ollama.com
- Pull the model: ollama run gemma:2b (or gemma:3b)

🚀 How to

…

View on GitHub

How I Built It

The game is built around two open-source models running on your own machine, behind a small FastAPI backend.

Riddles: Gemma via Ollama. The backend takes a street name and asks a local Gemma model (gemma:2b by default) to write a riddle in a Harry Potter style. The model is configurable through the OLLAMA_MODEL and OLLAMA_URL environment variables.
Sign verification: Tesseract OCR. When you submit a photo, Tesseract reads the text and the backend checks whether it matches the target street.
Quest generation: OpenStreetMap. The backend takes your GPS position, calculates a point a set distance away in a random direction, and asks OpenStreetMap for the road name there.
Frontend: Svelte + Vite + Leaflet. It runs in the phone browser with a live map. A "Wand Setup" screen lets you point the app at your computer's backend over the local Wi-Fi.

Why Does Open Innovation Matter?

Because the models are open, the whole game runs on a laptop with no API keys, no usage bills, and no accounts. That matters for a game aimed at kids and families.

No cost per riddle. A closed API charges for every riddle, so a hobby game would eventually have to become a paid product. A local Gemma model can generate unlimited riddles for free.
Photos stay on your machine. Verification happens in local Tesseract, so pictures of streets and surroundings never go to a third party.
Anyone can swap the model. Changing one environment variable switches to a different Ollama model, so people can pick whatever their hardware can run.
It works because the pieces are open. Ollama, Gemma, Tesseract, Leaflet, and OpenStreetMap fit together without negotiating access to anything.

My Agent Session

Building an Offline Local AI Street Hunt App

You

Make the questions more on the name of the sign and make the leaderboard local storage

Agent

I've made the requested changes! Removed backend leaderboard, updated Ollama prompt to focus heavily on the street name, and made the leaderboard purely localStorage based.

You

how does it know there is street sign there??

Agent

Great question! The app relies on OpenStreetMap to pick a real street nearby. It doesn't know there's a physical sign, it just relies on the assumption that real streets have signs.

Prize Categories

Best Use of Gemma: Street Hunt generates every riddle with a local Gemma model (gemma:2b by default) running through Ollama. The model is swappable through an environment variable, so players can use whichever Gemma size their hardware can handle.

Simple English Translator (Gemma 2B Chrome Extension)

Athul — Sun, 04 Oct 2026 06:29:31 +0000

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

What I Built

My mother's first language is not English, but she loves reading—especially the News and Wikipedia. However, the language used is often hard for her to understand.
So I built a Simple English Translator and Read-out-Loud Chrome extension

Demo

Code

https://github.com/42lv88/TranslateIntoSimpleEng

How I Built It

I built a standard English-to-Simple-English translator with a read-out-loud feature using Gemma 2B and the ElevenLabs API.

Why Does Open Innovation Matter?

I don't want big companies making ad revenue from what my mother translates or listens to. Having open-source software that runs locally on her laptop makes the experience much more private, secure, and beautiful.

Mother's Reaction

She did not care for it much, and said she loves calling me for help with translations once in a while.

Prize Categories

ElevenLabs and Gemma
Best Use of Gemma
Best Use of ElevenLabs

Total noob

Athul — Fri, 02 Oct 2026 09:59:47 +0000