DEV Community: sarvesh Linux

Python AI helper

sarvesh Linux — Sun, 25 Oct 2026 18:45:14 +0000

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

What I Built

I built a Python Helper AI Learning Lab — a lightweight learning companion for anyone who wants to explore Python with the help of AI.

The project helps learners:

understand Python concepts in plain language
get beginner-friendly explanations for code snippets
practice common patterns and examples
ask for guidance without needing a full coding mentor on demand
move from “I copied this code” to “I understand what it does”

In other words, it turns Python learning into a more interactive, guided experience — especially helpful for beginners, students, and self-taught developers who want a smarter, more approachable way to learn.

Demo

Live demo: https://your-username.github.io/python-helper-ai-learning-lab/

This is a GitHub Pages demo of the app, where you can try the learning flows and interact with the Python helper experience.

Code

Repository: https://github.com/your-username/python-helper-ai-learning-lab

This project is open source and available for anyone to explore, learn from, and improve.

How I Built It

I built this using a simple, beginner-friendly stack focused on accessibility and experimentation:

Python for the core logic
Open-source AI tooling and local/open-weight model support
Lightweight front-end or notebook-style interface for interaction
Simple prompts and educational workflows to explain code, concepts, and debugging help

The idea was to keep the project useful without making it dependent on a closed, proprietary AI service. By leaning on open-source AI tooling and open-weight models, the app is easier to study, adapt, and improve — and it makes learning more transparent and accessible.

Why Does Open Innovation Matter?

Open innovation matters because learning tools should be transparent, adaptable, and community-driven.

With open-source AI, it becomes possible to:

build learning experiences that are not locked behind a paid API
customize the tool for specific educational needs
experiment with better prompts, better explanations, and better learning flows
make the project accessible to more people around the world

A closed API might give a quick prototype, but open innovation allows a project like this to grow into a real educational resource with room for collaboration, iteration, and improvement.

My Agent Session

I saved my agent session while building and iterating on the project, and I’ll add the link here once it’s published or shared.

The Lazy Payoff

This project saves time in two big ways:

it reduces the “stuck on a Python concept” delay
it gives learners a faster way to get explanations and examples without having to search through multiple tutorials or ask someone else every time

For a self-learner or beginner, that means less friction and more momentum. Instead of getting blocked for 30–60 minutes on one idea, they can get a clear explanation and keep learning.

I used it as a practical learning and experimentation tool while iterating on the concept, and it made working through Python ideas much more efficient.

AI League-Coach

sarvesh Linux — Sun, 18 Oct 2026 20:41:20 +0000

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

What I Built

League Coach is a stats-driven coach for League of Legends. You give it match stats (CS, deaths, vision, KDA, win/loss per game). It compares them to role benchmarks, finds your biggest gaps, and a local LLM turns them into a short coaching plan: your biggest problem, three drills for your next five games, and one thing you do well.

Who would pay: ranked grinders stuck in a rank who can't afford human coaching ($20-50/hour), and small coaches or Discord communities who want to triage students' stats before a session. Possible pricing: a free CLI, then a paid hosted version with Riot API auto-import and a weekly progress report.

Demo

sarvesh-amb.github.io

Code

Sarvesh-Amb / league-coach

this is completely ai generated, I just wanted the sticker I am sorry :( it's supposed to be a league coach, at least I hope it works well

View on GitHub

How I Built It

Rules engine (pure Python, stdlib only): groups games by role and computes CS/min, vision/min, deaths in wins vs losses, and KDA. It ranks gaps against editable role benchmarks. The numbers come from code, not the model, so the LLM can't make up your stats.
Open-weight LLM via Ollama: the flagged gaps go to a local model (Llama 3.1 8B by default; Qwen 2.5 and others work via --model), which writes the coaching under a strict "use only these numbers" system prompt.
Graceful fallback: if no model is running, you still get the rules-based findings.

Why Does Open Innovation Matter?

A coach is only useful if you run it after every session, so cost per run matters. With open weights it's free to run locally with no API key or rate limits. Your match history stays on your machine. And anyone can swap in a better model or edit the benchmarks for their own role, patch, or game, which a closed API wouldn't let me promise users.

TREE-DEX AI, capture all the trees!

sarvesh Linux — Sun, 11 Oct 2026 18:03:36 +0000

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

What I Built

Demo

<-- https://claude.ai/artifact/3jRV2DrbVkgPXxigM7zhT7#play-15dd8cd198dd -->
<-- you need the gemma modal running locally for this to work -->

Code

https://github.com/Sarvesh-Amb/TreeDex

How I Built It

<--usiing anthorpic's claud ai I made a locally hosted ai that uses gemma to install-->

Why Does Open Innovation Matter?

<-- practive new ideas and build cool stuff -->

AI python Helper for my Little Brother

sarvesh Linux — Mon, 05 Oct 2026 02:04:06 +0000

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

What I Built

I build an AI python helper for my little brother, The ai will not give the answer directly to the user but guide them through the journey. there is also a few lessons that the user can go thorugh to get their feet off the ground with python ^ _ ^

Demo

https://youtu.be/wkfLDCMAg3c

Code

https://github.com/Sarvesh-Amb/PythonHelperAI

How I Built It

My project utalizes Ollama and the qwen2.5-coder:7b parameter model and python to have a conversation with the user and help them learn python. The project is ment for bigenners to get started with python!

Why Does Open Innovation Matter?

you control your data, you know where everything goes and it's fun to build your own thing !