DEV Community: Shivam Kumar Jha

# 🦥 DataJanitor AI — From Raw Data to Real Insights

Shivam Kumar Jha — Thu, 22 Oct 2026 05:29:45 +0000

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

🦥 DataJanitor AI — From Raw Data to Real Insights

What I Built

Data analysis shouldn't require hours of manual exploration, repetitive plotting, or writing boilerplate machine-learning code.

That's why I'm building DataJanitor AI — an AI-powered data exploration and machine-learning platform that helps users go from raw datasets to meaningful insights with less effort.

The goal is simple: upload your data, understand it, visualize it, and eventually train machine-learning models without writing everything from scratch.

📊 Phase 1: Smart Data Visualization

Users can upload CSV or Excel files and explore their datasets through:

Univariate Analysis: Understand individual variables using histograms, box plots, bar charts, and descriptive statistics.
Bivariate Analysis: Discover relationships between two variables using scatter plots, correlation analysis, grouped comparisons, and other suitable visualizations.
Multivariate Analysis: Explore patterns across multiple variables through correlation heatmaps, pair plots, and more advanced visualizations.
Dataset Profiling: Identify column types, missing values, duplicate records, and potential data-quality issues.
AI-Powered Insights: Generate plain-language explanations of statistical patterns and visualization results.

🤖 Phase 2: Machine Learning

The next milestone is to let users select their input features (X) and target variable (y) and train machine-learning models directly from the interface.

Planned capabilities include:

Automatic classification and regression task suggestions.
Data preprocessing and train-test splitting.
Training and comparing suitable machine-learning models.
Evaluation metrics and feature-importance visualizations.
Predictions on new data and downloadable model artifacts.

The idea is to make data exploration and machine learning more accessible to students, developers, analysts, and anyone working with structured data.

Code

GitHub Repository: DataJanitor AI

How I Built It

I'm building DataJanitor AI with an open-source-first approach.

Planned technology stack:

Frontend: React + Tailwind CSS for an interactive analytics dashboard.
Backend: Python + FastAPI for dataset processing and analysis APIs.
Data Processing: Pandas and NumPy for data profiling and statistical calculations.
Visualizations: Plotly for interactive charts and exploration.
Machine Learning: Scikit-learn for preprocessing, training, and evaluation.
Open-Weight AI: Gemma or another compatible open-weight model, served locally through Ollama, for natural-language explanations and dataset insights.

The application will use deterministic statistical calculations for numerical results and machine-learning evaluation. The AI layer will help explain findings in understandable language rather than inventing statistics.

The planned workflow is:

Upload → Profile → Visualize → Understand → Train → Predict

Why Does Open Innovation Matter?

Data can be sensitive. A dataset may contain business records, customer information, financial figures, or research data that users don't want to send to an external service.

Open innovation gives DataJanitor AI the flexibility to support local inference, model choice, and transparent data-processing workflows.

By using open-source libraries and compatible open-weight models, the project aims to:

Keep sensitive datasets on the user's machine when using the local workflow.
Reduce reliance on proprietary AI APIs for dataset explanations.
Allow users to experiment with different models.
Make core statistical analysis and machine-learning workflows accessible without depending on a paid AI service.

For this project, AI should make analysis easier — not make users dependent on a black box.

My Agent Session

Optional — I'll add a DevRelay agent session or development trace here if available.

The Lazy Payoff

Imagine uploading a spreadsheet and getting an initial understanding of its structure, distributions, relationships, and potential data-quality problems without manually creating every chart.

Instead of spending time on repetitive analysis setup, users can focus on interpreting results and making decisions.

The longer-term goal is to make the journey from a raw dataset to a trained predictive model much simpler.

Prize Categories

The following are the partner categories I'm considering for DataJanitor AI. I'll include only the categories supported by the final implementation.

Best Use of Gemma — Use Google's open-weight Gemma model for dataset explanations and AI-generated insights.
Best Use of TabPFN — Integrate TabPFN for suitable tabular classification or prediction tasks in the machine-learning phase.
Best Use of DigitalOcean — Deploy the application or serve its AI component using DigitalOcean infrastructure.
*Best Use of Tinker * — Fine-tune an open-weight model for chart recommendations or structured data-analysis planning and evaluate it against the base model.

devchallenge #hf26challenge #ai #machinelearning #datascience #opensource #python #react #exploratorydataanalysis #automl

FreelanceFlow AI: Turn Messy Client Briefs into Proposals with a Local LLM

Shivam Kumar Jha — Wed, 14 Oct 2026 15:07:07 +0000

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

What I Built

FreelanceFlow AI turns a messy client brief into a structured, editable project proposal, and it runs entirely on your own machine.

Every freelancer knows this unpaid part of the job: a client sends a rambling email ("we need a simple website… maybe show our Instagram?… budget around $2k"), and before any paid work starts you have to work out the real requirements, split them into deliverables and milestones, spot what's missing, and write a professional proposal. For people doing this as a side hustle, that's an evening gone for every quote.

FreelanceFlow AI does it in three steps:

Extract: paste the brief, and a local open-weight model pulls out the project title, summary, requirements, deliverables, milestones, deadline, budget, assumptions, and questions you should ask the client.
Review: every field can be edited. You fix what the model got wrong before anything is written.
Draft: add your name, your rate, and a tone, and get a Markdown proposal you can edit, copy, or download.

One rule is fixed: the AI never invents your price. If you don't enter a rate, the proposal says [Your rate].

Who would pay for it? Freelance developers, designers, and small agencies who send several proposals a week and don't want to paste confidential client details into a cloud chatbot. Faster quoting means more bids and less unpaid admin.

Code

jhashivam0022 / freelanceflow-ai

An open-source AI assistant that turns freelance client briefs into structured project proposals using open-weight language models.

freelanceflow-ai

An open-source AI assistant that turns freelance client briefs into structured project proposals using open-weight language models.

View on GitHub

How I Built It

Model runtime: Ollama for local inference. Any Ollama chat model works through one environment variable (OLLAMA_MODEL).
Models: developed and tested with Google's open-weight Gemma (gemma:2b), with Qwen 2.5 7B recommended for better extraction.
Backend: Python + FastAPI. The key design decision was splitting the work into two model calls:
1. Structured extraction. I pass a Pydantic model's JSON schema straight to Ollama's format parameter (structured outputs), so even a 2B model has to return valid, typed JSON. The backend validates it again with Pydantic and returns a clean error if the model goes off the rails.
2. Proposal drafting. A second call writes the proposal using the human-reviewed scope as the source of truth, not the raw brief.
Frontend: React + Vite. A three-step flow with an editable scope view in the middle.
Tests: pytest with a fake LLM, so the API logic is tested without a GPU.

What I learned: small local models are good at reading a brief but still miss details. In testing, gemma:2b skipped a budget and deadline that were clearly in the brief and added a milestone nobody asked for. Instead of hiding that, I made human review a required step. The AI does the boring 80%, and the freelancer checks the 20% that matters.

Why Does Open Innovation Matter?

Client briefs are confidential: budgets, unreleased products, internal plans. Many freelancers are under NDA and shouldn't paste that into a third-party AI service.

Open-weight models change that:

The brief never leaves your laptop. Browser → local FastAPI → local Ollama. No third-party API in the loop.
Zero cost per proposal. A side-hustle tool shouldn't charge you every time you bid on a job.
No lock-in. Switching from Gemma to Qwen to Llama is one config change, so the tool improves as open models improve.
Runs on what you have. A 2B model works on a normal laptop, and a bigger GPU gets you a bigger model.

A closed API would have made the core promise ("your client's data stays with you") impossible.

Prize Categories

Best Use of Gemma: FreelanceFlow AI was developed and tested with Google's Gemma (gemma:2b) via Ollama for both structured requirement extraction and proposal drafting.

Built with help from an AI coding assistant.

🌿 AI Outdoor Quest: An Open-Source AI That Gets You Outside

Shivam Kumar Jha — Tue, 06 Oct 2026 07:41:06 +0000

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

What I Built

What if we used AI for the opposite of what we normally use it for?

Instead of giving people another reason to stay on their screens, AI Outdoor Quest gives people a reason to go outside.

AI Outdoor Quest is an open-source AI-powered outdoor mission generator.

You tell it something simple like:

"I have 30 minutes and want to do something outside."

AI Outdoor Quest turns that into a personalized outdoor quest based on your time, interests, and activity.

For example:

🌳 Find three different types of trees
🚶 Walk for 10 minutes
👂 Stop and notice three different sounds
📸 Find something you've never noticed before
🧭 Explore a different route
🧘 Spend five minutes outside without looking at your phone

The idea is simple:

Start a quest → put the phone away → go outside. 🌿

The screen should be the shortest part of the experience.

Code

💻 GitHub: - AI Outdoor Quest

The project is being developed openly as part of Hacktoberfest 2026.

How I Built It

AI Outdoor Quest is built around open-weight AI.

The AI is used as the quest-planning engine. It takes the user's available time, preferences, and activity goals and turns them into a structured outdoor experience.

The broader application is being designed around:

🤖 Gemma — personalized outdoor quest generation
🌐 SerpApi — live information for context-aware quests
🧠 MongoDB Atlas — storing quest history and user preferences
🔊 ElevenLabs — voice guidance so users don't need to constantly look at their screen
⏱️ Temporal — durable and resumable outdoor quests
📊 Sentry — AI agent tracing and observability
☁️ DigitalOcean — application and AI infrastructure

Each technology has a specific role in the application rather than being added just for the sake of using another tool.

Why Does Open Innovation Matter?

AI is increasingly becoming something we interact with through a screen.

I wanted to try the opposite:

What if AI helped us spend less time with technology?

Using open-weight AI gives the project the flexibility to experiment with different models, customize how quests are generated, and run the AI locally where practical.

It also means the project can evolve for different types of outdoor activities and communities.

The AI doesn't need to keep you talking to it.

Its job is to give you something to do in the real world.

Prize Categories

🟢 Gemma — using an open-weight Gemma model for personalized outdoor quest generation.
☁️ DigitalOcean — deploying the application and supporting AI infrastructure on DigitalOcean.
🔊 ElevenLabs — providing voice guidance so users can follow quests without constantly looking at their screen.
🌐 SerpApi — using live search to make outdoor quests more relevant to the user's surroundings.
🧠 MongoDB Atlas — storing outdoor experiences and preferences for longer-term personalization.
📊 Sentry Agent Tracing — tracing and understanding the AI agent's execution.
⏱️ Temporal — making longer-running outdoor quests durable and resumable.

🌿 Start a quest. Put the phone away. Go outside.

BugReplay: Helping Developers Learn from Bugs Their Team Has Already Solved 🐛

Shivam Kumar Jha — Fri, 02 Oct 2026 06:42:05 +0000

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

Ever spent hours debugging an issue, only to find out your teammate had already fixed the exact same bug? 💀

That's where BugReplay comes in! 🚀

I'm building an AI-powered debugging assistant that helps teams turn their past bug fixes into reusable knowledge.

💡 The idea

Instead of digging through old chats, GitHub issues, or asking teammates for the same solution, developers can simply paste an error message or stack trace into BugReplay and find relevant issues the team has already resolved.

⚡ What it does

🔍 Find Similar Bugs: Uses semantic search to find related, previously resolved issues.
🧠 Understand Root Causes: Shows how similar problems occurred and what fixed them.
🤖 AI-Powered Guidance: Provides troubleshooting suggestions based on the team's verified solutions.
📚 Build Team Knowledge: Saves newly resolved bugs so the whole team can benefit.
🤝 Learn Together: Helps teammates debug independently while allowing mentors to review and verify solutions.

🛠️ Tech Stack

Frontend: React
Backend: Python + FastAPI
AI: Qwen (open-weight model)
Database: PostgreSQL + pgvector
AI Workflow: Retrieval-Augmented Generation (RAG)

🎯 Why BugReplay?

Every bug a team solves is experience worth keeping. But that knowledge often gets lost in chats, scattered across GitHub issues, or stays with the person who fixed it.

BugReplay aims to make that experience accessible to everyone on the team, reduce repeated debugging, and help developers solve problems with more context.

🌱 Building for a Friend

I'm building BugReplay with my teammates in mind. The goal is to make debugging a shared learning experience, where everyone can benefit from problems the team has already solved.

🚀 Solve it once. Save the fix. Replay the learning.

I'm excited to build this and explore how open-weight AI can help solve real-world problems for development teams.

🔗 Code: GitHub Repository - https://github.com/jhashivam0022/bugreplay.git

More updates and a demo coming soon!

devchallenge #weekendchallenge #hf26challenge #AI #opensource #developers

Hello, DEV Community! 👋

Shivam Kumar Jha — Fri, 02 Oct 2026 05:36:05 +0000

Hello everyone! I'm Shivam Kumar Jha, an AI/ML Engineer and Full Stack Developer passionate about building intelligent solutions and scalable applications. 🚀

I graduated with a B.Tech in Computer Science and Engineering (AI & ML) and enjoy exploring how Artificial Intelligence and software development can solve real-world problems.

💻 My Technical Interests

🤖 Artificial Intelligence & Machine Learning
🧠 Deep Learning and Computer Vision
🌐 Full Stack Development
🐍 Python, PyTorch, TensorFlow
⚛️ React.js, Java, Spring Boot
🗄️ PostgreSQL, REST APIs
☁️ Cloud Technologies: AWS and DigitalOcean

🚀 What I Do

I have hands-on experience developing AI/ML projects, building web applications, designing REST APIs, and working with cloud deployments. I enjoy taking ideas from concept to implementation and continuously improving my technical skills.

🌱 Why I'm Here

I'm joining the DEV Community to:

Learn from developers and engineers around the world.
Share my technical knowledge, projects, and experiences.
Explore open-source contributions.
Connect with like-minded people and grow together🤝.

DEVCommunity #AI #MachineLearning #DeepLearning #FullStackDevelopment #Python #ComputerVision #OpenSource

DEV Community: Shivam Kumar Jha

# 🦥 DataJanitor AI — From Raw Data to Real Insights

🦥 DataJanitor AI — From Raw Data to Real Insights

What I Built

📊 Phase 1: Smart Data Visualization

🤖 Phase 2: Machine Learning

Code

How I Built It

Why Does Open Innovation Matter?

My Agent Session

The Lazy Payoff

Prize Categories

Tags

devchallenge #hf26challenge #ai #machinelearning #datascience #opensource #python #react #exploratorydataanalysis #automl

FreelanceFlow AI: Turn Messy Client Briefs into Proposals with a Local LLM

What I Built

Code

jhashivam0022 / freelanceflow-ai

An open-source AI assistant that turns freelance client briefs into structured project proposals using open-weight language models.

freelanceflow-ai

How I Built It

Why Does Open Innovation Matter?

Prize Categories

🌿 AI Outdoor Quest: An Open-Source AI That Gets You Outside

What I Built

Code

How I Built It

Why Does Open Innovation Matter?

Prize Categories

BugReplay: Helping Developers Learn from Bugs Their Team Has Already Solved 🐛

devchallenge #weekendchallenge #hf26challenge #AI #opensource #developers

Hello, DEV Community! 👋

DEVCommunity #AI #MachineLearning #DeepLearning #FullStackDevelopment #Python #ComputerVision #OpenSource