DEV Community: Ajay Dhangar

AI Buddies: Lazy-Mode Learning for Developers

Ajay Dhangar — Tue, 20 Oct 2026 08:58:12 +0000

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

What I Built

Learning complex algorithms and navigating huge codebases takes hours of tedious reading, manually tracing variable changes on paper, and digging through endless stack traces.

I built AI Buddies to make learning and debugging entirely effortless. Instead of forcing you to read walls of text or debug step-by-step manually, AI Buddies automates the entire comprehension workflow. It visualizes data structures dynamically, breaks down complex logic into bite-sized summaries, and guides you through problem-solving without making you scratch your head for hours.

Who gets to be a little lazier because of it?

Computer Science Students: Skip spending 3 hours tracing recursion trees on paper—AI Buddies renders the execution tree instantly.
Self-Taught Developers: Stop opening 20 browser tabs to understand a single algorithm concept—get step-by-step hints served directly in your sandbox.
Open-Source Maintainers: Automate onboarding and documentation breakdowns so new contributors don't constantly ask basic setup questions.

Demo

Live Platform: ai-buddies
Interactive Visualizers: Trace algorithms and test interactive agentic roadmaps effortlessly in your browser.

Code

ajay-dhangar / ai-buddies

Learn AI through hands-on projects, interactive learning paths, and community-driven content. Explore machine learning, deep learning, NLP, computer vision, and more. Stay updated with cutting-edge trends and build real-world AI skills.

Website

This website is built using Docusaurus, a modern static website generator.

Installation

npm install

Local Development

npm start

This command starts a local development server and opens up a browser window. Most changes are reflected live without having to restart the server.

Build

npm run build

This command generates static content into the build directory and can be served using any static contents hosting service.

Deployment

Using SSH:

$ USE_SSH=true npm run deploy

Not using SSH:

$ GIT_USER=<Your GitHub username> npm run deploy

If you are using GitHub pages for hosting, this command is a convenient way to build the website and push to the gh-pages branch.

View on GitHub

How I Built It

To keep response times lightning fast and fully automated, AI Buddies relies on a modern open-source AI architecture:

Frontend & Visual Engine: Built with React, TypeScript, Tailwind CSS, and Docusaurus. Custom visual components render interactive step-by-step flowcharts and KaTeX math formulas automatically.
Open AI & Agent Harnesses: Powered by open-weight model integration and agent frameworks (such as Hugging Face open weights, LangChain agent pipelines, and local inference via Ollama).
Automated Routing: Agents parse user queries or code snippets, auto-select the best open model for the job (fast syntax breakdown vs. full logic tracing), and return interactive UI previews instead of long, boring text responses.

Why Does Open Innovation Matter?

"Slow and Steady" means building sustainable tools that run anywhere, anytime, without relying on unpredictable third-party services or recurring API bills. Open innovation makes this possible:

Zero Operating Overhead: Closed APIs charge per token and per request, which punishes users who learn at their own pace. Open weights and local inference let students run agentic workflows continuously for free.
Offline & Low-Spec Execution: Lightweight open models run directly on modest hardware without needing high-speed internet. You can learn on a train, in a low-bandwidth area, or on an older laptop.
Custom Agent Rules: Closed models often try to solve the entire problem instantly, taking away the learning opportunity. Open frameworks let us explicitly program agentic behaviors to gently guide, hint, and visualize.

My Agent Session

(Optional: Insert your saved DevRelay session link or tag here if you recorded your development workflow!)

The Lazy Payoff

This week, I used AI Buddies to walk through a complex graph traversal problem that usually takes 45–60 minutes of manual diagramming and trial-and-error debugging.

Time Saved: Cut understanding and implementation time down from 1 hour to under 10 minutes.
Effort Saved: Zero paper diagrams needed. The automated visualizer rendered node visit sequences and queue states step-by-step with a single click.

Prize Categories

Main Track: Slow and Steady
Open Source AI / Local Inference Track

Building AI Buddies: An Open AI Learning Companion for CodeHarborHub

Ajay Dhangar — Fri, 16 Oct 2026 03:36:31 +0000

This is a submission for the MLH x DEV Writing Challenge

What I Built

Learning Data Structures, Algorithms, and full-stack development can feel daunting when you're navigating complex documentation alone. As the maintainer of CodeHarborHub, an open-source platform dedicated to empowering developers through structured learning paths. I wanted to create an interactive tool to make self-paced technical education truly engaging.

I built AI Buddies, an open-source AI learning partner integrated within the CodeHarborHub ecosystem. Instead of acting as a typical chatbot that dumps ready-made answers, AI Buddies provides step-by-step guidance, breaks down algorithm concepts with real-time visualizers, and acts as a patient partner for learners solving coding challenges in an interactive sandbox.

Key Learnings:

Designing non-intrusive AI agents that guide learning rather than completing tasks for the user.
Structuring lightweight MDX and React execution environments for seamless browser rendering.
Balancing client-side interactivity with open-weight model architectures.

Demo

Live Platform: AI Buddies
Main Ecosystem: CodeHarborHub
Interactive Roadmaps: Explore live data structure visualizers and agentic learning modules directly in the browser.

Code

ajay-dhangar / ai-buddies

Learn AI through hands-on projects, interactive learning paths, and community-driven content. Explore machine learning, deep learning, NLP, computer vision, and more. Stay updated with cutting-edge trends and build real-world AI skills.

Website

This website is built using Docusaurus, a modern static website generator.

Installation

npm install

Local Development

npm start

This command starts a local development server and opens up a browser window. Most changes are reflected live without having to restart the server.

Build

npm run build

This command generates static content into the build directory and can be served using any static contents hosting service.

Deployment

Using SSH:

$ USE_SSH=true npm run deploy

Not using SSH:

$ GIT_USER=<Your GitHub username> npm run deploy

If you are using GitHub pages for hosting, this command is a convenient way to build the website and push to the gh-pages branch.

View on GitHub

You can also check out our wider open-source organization:

codeharborhub / codeharborhub.github.io

Our mission is to provide accessible and comprehensive educational resources to learners of all levels, from beginners to advanced professionals. Whether you're looking to kickstart your career in web development, master a new programming language, or stay updated on the latest tech trends, we've got you covered.

Welcome to CodeHarborHub! Your gateway to top-notch tech education. Tired of limitations? CodeHarborHub shatters them. We're the exclusive platform offering a comprehensive tech curriculum, taught by industry masters, completely free. Join our vibrant community, master in-demand skills, and launch your dream tech career.

About

At CodeHarborHub, our mission is clear: to provide accessible and comprehensive educational resources to learners of all levels, from beginners to advanced professionals. Whether you're a novice or a seasoned developer, our inclusive platform offers tailored learning opportunities. Join us today and embark on your path to tech mastery!

Features

In-Depth Tutorials: Dive into comprehensive tutorials covering a wide range of web development topics.
Courses for Mastery: Enroll in structured courses designed to take your skills to the next level.
Inspiring Showcases: Explore inspiring showcases of real-world projects and innovative web solutions.
Engaging Community: Connect with a vibrant community of developers, share…

View on GitHub

Partner Technologies

To keep the platform fast, responsive, and open for global contributors, I utilized several core technologies and developer platforms:

GitHub & GitHub Actions: Used for hosting our repositories, managing open-source contributor pull requests, and orchestrating CI/CD pipelines to build and deploy docs and interactive components automatically.
Open AI & Agent Harnesses: Integrated open-weight model routing and agent framework concepts (such as LangChain and Hugging Face open weights), enabling learners to leverage model flexibility without vendor lock-in.
Frontend Stack: Built using React, TypeScript, Tailwind CSS, and Docusaurus for fast, modern documentation layouts with interactive live code previews and KaTeX notation support.

Implementing these tools allowed us to maintain zero-cost inference paths for students while giving them full control over model customization and data privacy.

Hackathon Experience

Participating in hackathons as part of the MLH community is always an invigorating experience. The collaborative atmosphere, late-night debugging sessions, and feedback loops with fellow hackers inspired many of the features now powering AI Buddies.

What I’ll remember most is sharing our live visualizers with student developers during community review rounds. Seeing learners instantly grasp a complex tree traversal or dynamic programming concept through an interactive agent session reminded me why open-source community building matters so much.

If you're interested in open-source AI or building developer tools, check out our repository and drop a star or PR!

AI Buddies: An Open AI Learning Micro-SaaS for Developers

Ajay Dhangar — Thu, 15 Oct 2026 03:41:23 +0000

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

What I Built

Self-taught developers, computer science students, and bootcamp grads spend hundreds of dollars on private tutors or generic AI chat subscriptions that just output pre-written code without explaining how or why it works.

I built AI Buddies as a Freemium Micro-SaaS learning partner platform. It offers guided, step-by-step Data Structures, Algorithms, and full-stack interactive paths powered by open-source AI.

Why would people pay for it?

While basic AI chatbots give flat answers, AI Buddies acts as an interactive tutor with real-time code visualizers, sandbox exercises, and step-by-step hint systems. Students and job seekers pay a small monthly subscription ($5–$10/month) for premium feature modules—such as personalized mock technical interview simulations, custom repository code analysis, and unlimited agentic learning workflows—at a fraction of the cost of traditional tutoring platforms.

Demo

Live Platform: ai-buddies
Interactive Visualizers: Try interactive roadmaps and agentic study paths live in your browser.

Code

ajay-dhangar / ai-buddies

Learn AI through hands-on projects, interactive learning paths, and community-driven content. Explore machine learning, deep learning, NLP, computer vision, and more. Stay updated with cutting-edge trends and build real-world AI skills.

Website

This website is built using Docusaurus, a modern static website generator.

Installation

npm install

Local Development

npm start

This command starts a local development server and opens up a browser window. Most changes are reflected live without having to restart the server.

Build

npm run build

This command generates static content into the build directory and can be served using any static contents hosting service.

Deployment

Using SSH:

$ USE_SSH=true npm run deploy

Not using SSH:

$ GIT_USER=<Your GitHub username> npm run deploy

If you are using GitHub pages for hosting, this command is a convenient way to build the website and push to the gh-pages branch.

View on GitHub

How I Built It

To keep operational overhead low enough for a profitable side hustle, AI Buddies relies on an open-source AI stack:

Frontend & Web UI: Built with React, TypeScript, Tailwind CSS, and Docusaurus for fast, lightweight rendering and interactive documentation layout.
Open AI & Agent Frameworks: Integrated open-weight model routing (via Hugging Face and local inference runners like Ollama / LangChain agent harnesses). This allows learners to connect their own local hardware or access lightweight hosted open weights without expensive API middleware.
Interactive Learning Tools: Built custom React and KaTeX components for mathematical notation, real-time code visualization, and algorithmic execution tracking.

Why Does Open Innovation Matter?

In a side hustle, unit economics make or break the business. Open innovation gave AI Buddies three distinct advantages over proprietary closed APIs:

Zero-Inference Cost Base: Proprietary LLM APIs charge per token, making high-volume student usage expensive. Using open weights and client-side or local inference options keeps server costs near zero, making a freemium pricing tier sustainable.
Data Privacy & Local Running: Learners often work with proprietary interview questions or sensitive codebases. Open-weight models run locally on the user's machine, keeping their data off third-party servers.
No Vendor Lock-In: Open agent harnesses let us swap specialized open-weight models (e.g., code-tuned weights vs. general explanation models) instantly without rewriting prompt pipelines or accepting price hikes.

My Agent Session

(Optional: Insert your saved DevRelay session link or tag here if you recorded your development workflow!)

My First User

I shared the live AI Buddies platform with a developer from my community who was preparing for technical interviews.

What they said:

"Regular AI chats just give away the solution immediately, which ruins the learning process for DSA. AI Buddies actually walks me through debugging step-by-step with visual diagrams. I would easily pay $10/month for the interview simulation module alone because it's cheaper than a single hour with a human tutor."

Prize Categories

Main Track: Side Hustle
Best Use of Gemma (If deploying Gemma open weights)
Best Use of DigitalOcean / Render (Depending on your hosting provider)

AI Buddies: An Open AI Learning Partner Built for a Friend

Ajay Dhangar — Mon, 05 Oct 2026 15:33:30 +0000

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

What I Built

Learning Data Structures, Algorithms, and full-stack development can feel overwhelming when you're doing it alone. I built AI Buddies for a friend and fellow developer in my community who was struggling to bridge the gap between reading heavy technical documentation and actually writing code. Closed, subscription-based AI models were either locked behind paywalls or just gave away full answers without teaching the core concepts.

AI Buddies is an interactive, open-source AI learning platform designed to act as a patient coding partner. Instead of just dumping ready-made solutions, it breaks down complex DSA concepts, explains code step-by-step with interactive visualizations, and guides learners through real-world programming challenges in a supportive, step-by-step sandbox environment.

When I handed it over to my friend to test, their reaction was:

"Having a companion that breaks down complex code without just handing me the answer makes learning complex algorithms way less intimidating."

Demo

Live Platform: ai-buddies
Live Interactive Visualizers & Roadmaps: Explore interactive learning modules and agentic study paths directly in the browser.

Code

ajay-dhangar / ai-buddies

Learn AI through hands-on projects, interactive learning paths, and community-driven content. Explore machine learning, deep learning, NLP, computer vision, and more. Stay updated with cutting-edge trends and build real-world AI skills.

Website

This website is built using Docusaurus, a modern static website generator.

Installation

npm install

Local Development

npm start

This command starts a local development server and opens up a browser window. Most changes are reflected live without having to restart the server.

Build

npm run build

This command generates static content into the build directory and can be served using any static contents hosting service.

Deployment

Using SSH:

$ USE_SSH=true npm run deploy

Not using SSH:

$ GIT_USER=<Your GitHub username> npm run deploy

If you are using GitHub pages for hosting, this command is a convenient way to build the website and push to the gh-pages branch.

View on GitHub

How I Built It

AI Buddies is built with a modern, performance-focused open-source web stack and agentic architecture:

Frontend Architecture: Built using React, TypeScript, Tailwind CSS, and Docusaurus for interactive, fast-loading documentation and web app rendering.
Open AI & Agent Frameworks: Integrated open-source AI routing and agent harnesses (such as Hugging Face open weights and local inference setups via Ollama/LangChain support), allowing learners to execute models seamlessly without vendor lock-in.
Interactive Visualizations: Uses KaTeX for mathematical/algorithmic notation and custom rendering components to help learners visualize data flows and logic step-by-step.

Why Does Open Innovation Matter?

Open innovation is the backbone of accessible technical education. Here is why an open-source AI approach made all the difference over closed APIs:

Zero Financial Barriers: Students and emerging developers shouldn't need a paid monthly subscription to access quality technical guidance. Open weights and local inference options ensure anyone can run and learn for free.
Model Flexibility & Swappability: Closed APIs lock you into one model's behavior and pricing. With an open architecture, learners can swap underlying models—choosing fast lightweight models for quick syntax checks or specialized coding weights for complex algorithm breakdowns.
Data Privacy & Offline Learning: Open-weight models can be run locally on a laptop without internet access, keeping user data, code, and project ideas completely private and off servers they don't control.

My Agent Session

(Optional: Insert your saved DevRelay session link or tag here if you recorded your building process!)

Prize Categories

Main Track: Build for a Friend
Open Source AI / Local Inference Track

I Built an AI Learning Companion for People Who Want to Learn by Building

Ajay Dhangar — Fri, 02 Oct 2026 07:44:15 +0000

For the Hacktoberfest Weekend Challenge: Build for a Friend, I wanted to build something that wasn't just another AI demo.

I wanted to build something that could actually help someone learn.

So I built AIBuddies.

👉 Live: https://ajay-dhangar.github.io/ai-buddies/

👉 Source: https://github.com/ajay-dhangar/ai-buddies

AIBuddies is an open-source AI learning companion that brings together learning paths, practical projects, interactive demos, and community-driven resources in one place.

The Problem

Learning AI can be overwhelming.

There are thousands of tutorials, courses, papers, GitHub repositories, tools, and frameworks.

But when someone is just starting, the difficult question is often:

"What should I learn next, and what should I build?"

I wanted to create something that makes that journey easier.

Instead of only reading theory, learners should be able to:

Learn → Build → Experiment → Understand → Share

That's the idea behind AIBuddies.

What's Inside AIBuddies?

The platform currently brings together different areas of AI learning, including:

🧠 Machine Learning fundamentals
🔥 Deep Learning with Python
👁️ Computer Vision
💬 NLP and AI applications
🛠️ Hands-on projects
🧪 Interactive AI demos
📚 Learning resources
🤝 Community-driven learning

There are also practical examples such as AI-powered chatbots, image recognition, voice assistants, text-to-speech, and style-transfer experiments.

The goal is not to make AI feel magical.

The goal is to make it understandable and buildable.

Why I Built It for a Friend

The inspiration behind this project is simple.

Imagine someone who wants to learn AI but doesn't know where to start.

They jump between YouTube, documentation, courses, GitHub repositories, and random tutorials.

After a while, they have consumed a lot of information but haven't built much.

I wanted AIBuddies to become the kind of resource I could send to that person and say:

"Start here. Pick a path. Build something. Keep going."

That's what Build for a Friend means to me.

Not necessarily building something for a person's specific job.

Sometimes it's building something that helps someone you care about become better at something they want to learn.

Why Open Source AI Matters

This project is part of CodeHarborHub, my open-source initiative focused on making technology education more accessible.

AIBuddies follows the same philosophy:

Learning should be open, practical, and community-driven.

Open-source AI makes this ecosystem even more interesting because learners can go beyond simply calling an API.

They can explore models, tools, implementations, experiments, and projects.

They can learn how things work.

They can modify them.

And eventually, they can contribute back.

That creates a much more interesting learning loop:

Learn
  ↓
Experiment
  ↓
Build
  ↓
Break Things
  ↓
Understand
  ↓
Contribute
  ↓
Help Someone Else

What I'm Exploring

While building AIBuddies, I'm also exploring how an AI education platform can evolve beyond static documentation.

Some areas I'm interested in developing further:

Interactive AI experiments
Project-based learning
AI-assisted learning experiences
Open-source model experimentation
Beginner → advanced learning paths
Community contributions
Practical AI challenges
More browser-based AI demos
Better project discovery
AI tools that help learners understand concepts

The long-term idea is bigger than a collection of tutorials.

I want AIBuddies to become a place where people learn AI by actually building AI.

Built as Open Source

AIBuddies is publicly available so developers and learners can explore the project, suggest improvements, and contribute.

Live Project: https://ajay-dhangar.github.io/ai-buddies/
GitHub: https://github.com/ajay-dhangar/ai-buddies
CodeHarborHub: https://codeharborhub.github.io/

What's Next?

This challenge is only the beginning.

I'm planning to continue improving AIBuddies with more practical learning paths, projects, experiments, and community contributions.

Because I don't think the best way to learn AI is to consume 100 tutorials.

Sometimes it's better to build one small thing, understand why it works, break it, fix it, and then build the next thing.

That's the learning experience I want AIBuddies to encourage.

Build for a Friend

For me, this challenge isn't just:

"Build something with AI."

It's:

"Build something that makes another person's journey easier."

And that's exactly what I wanted AIBuddies to be.

If you're learning AI, I'd love for you to explore it.

If you're building something similar, I'd love to see it.

And if you have an idea for how AIBuddies could help learners better, feel free to contribute or open an issue.

Let's make AI learning more open, practical, and fun.

Placeholder Maintainer

Ajay Dhangar — Thu, 16 Oct 2025 02:50:59 +0000

👋 Intro

Hey everyone! I’m Ajay Dhangar, an open-source enthusiast, full-stack web developer, and the founder of CodeHarborHub.

This year, I participated as a Hacktoberfest 2025 Maintainer, and it has been an incredible learning experience. I’ve contributed as a maintainer before, but this year was special — with more contributors, better workflows, and deeper community interaction.

You can check out my GitHub here:

ajay-dhangar (Ajay Dhangar) · GitHub

github.com

Project

My hosted repository for Hacktoberfest was:

codeharborhub / codeharborhub.github.io

Our mission is to provide accessible and comprehensive educational resources to learners of all levels, from beginners to advanced professionals. Whether you're looking to kickstart your career in web development, master a new programming language, or stay updated on the latest tech trends, we've got you covered.

About

Features

In-Depth Tutorials: Dive into comprehensive tutorials covering a wide range of web development topics.
Courses for Mastery: Enroll in structured courses designed to take your skills to the next level.
Inspiring Showcases: Explore inspiring showcases of real-world projects and innovative web solutions.
Engaging Community: Connect with a vibrant community of developers, share…

View on GitHub

CodeHarborHub is an open-source learning platform offering tutorials, documentation, and community-driven projects for developers.

As a maintainer, I focused on:

Creating clear contribution guidelines and issue templates
Managing pull requests using GitHub Actions for automation
Reviewing PRs efficiently and merging with proper checks
Supporting contributors through discussions and mentorship

I also introduced a contributor scoring system and auto-comment bots to keep engagement high and ensure fair recognition of all contributions.

Highs and Lows

The most rewarding moment was seeing first-time contributors successfully complete their PRs and share excitement about open-source for the first time.

On the flip side, managing a large influx of PRs and resolving merge conflicts was challenging especially when contributors submitted similar fixes. But, through collaboration and improved documentation, we made it work smoothly.

A lightbulb moment was automating repetitive maintainer tasks using GitHub Actions, saving hours of manual review and improving consistency.

Growth

Before Hacktoberfest 2025, my focus was mainly on building and managing personal projects. Through this maintainer journey, I honed my community management, code review, and automation skills.

I also learned how to better structure large-scale open-source repositories for long-term sustainability.

After Hacktoberfest, my goal expanded not just to build projects but to build open communities that empower learning and contribution.

Web hosting issues || GitHub Page is not showing up on the website?

Ajay Dhangar — Fri, 23 Sep 2022 08:41:50 +0000

I have created one repository on GitHub and hosted it with the help of the GitHub page. My issue is that if I have put all code (CSS and JavaScript code) in HTML, then it works, but if I have created another folder of CSS and JavaScript and saved the path in HTML, then it's not working. I don't understand why.

For example, you create one simple hello world website and try code from this condition.

Repository link:

ajay-dhangar / ajay-dhangar.github.io

👋 Hi there! Welcome to my portfolio repo! I'm Ajay Dhangar, a software engineer and tech enthusiast passionate about web development, open source, and building cool stuff. Currently working at a startup and mentoring at CodeHarborHub.

Overview

Welcome to my portfolio website! I'm Ajay, an aspiring Full Stack Developer passionate about building clean, efficient, scalable solutions. This site showcases my skills, projects, and experiences, all crafted using modern technologies like React.js, TypeScript (TSX), MDX, and Docusaurus.

About Me

Seeking Full Stack Development Opportunities

Hi! I'm Ajay, a software engineer specializing in the MERN stack (MongoDB, Express.js, React.js, Node.js). I thrive on solving complex problems and turning ideas into real-world solutions. My approach is driven by curiosity and collaboration, and I always aim to write clean, maintainable, and efficient code.

Technologies Used

This portfolio website was built using the following technologies:

React.js: A JavaScript library for building user interfaces.
TypeScript (TSX): A typed superset of JavaScript that adds static types to your code, helping you catch errors early.
MDX: A format that lets you seamlessly write JSX in your Markdown documents.
Docusaurus: A…

View on GitHub

Website link:

Hello from Ajay Dhangar | Ajay Dhangar

Welcome to my portfolio website. I'm Ajay Dhangar, a passionate web developer and designer. Explore my projects, skills, and certifications.

ajay-dhangar.github.io