DEV Community: Gunjan

GhostShell

Gunjan — Wed, 28 Oct 2026 10:32:44 +0000

👻 GhostShell — Giving My Terminal a Ghost of Its Own

What if your terminal had a ghost living inside it?

For Ghost in the Machine, I'm exploring GhostShell, an open-source AI-powered terminal companion that brings a little supernatural personality to everyday development.

🕯️ The idea

A haunted terminal that reacts to commands with eerie commentary.
AI-generated ghost stories inspired by development sessions.
Optional warnings about potentially dangerous shell commands.
Local AI inference to keep terminal data private.

🧠 Powered by open AI

The project uses Python, Ollama, and a compatible open-weight language model. Instead of relying on a closed cloud API, GhostShell is designed to run its core AI experience locally, giving developers more control over their data, models, and customization.

🔓 Why open innovation matters

Your terminal history can reveal a lot about your projects and workflow. Keeping inference local means that information doesn't need to be sent to an external AI service. Open models also make it possible to experiment with different personalities, swap models, and keep the experience running offline after setup.

This Halloween, I'm bringing a little life to the command line — without giving the ghost control of my machine. 👻💻

OpenSourceAI #LocalAI #Ollama #Python #Hacktoberfest #GhostInTheMachine

🦥 SlothMode AI: Let Your Local AI Handle the Busywork

Gunjan — Sat, 24 Oct 2026 18:40:34 +0000

What if you could stop wasting time organizing files, reading lengthy study notes, and planning every little task?

That's the idea behind SlothMode AI — a local-first productivity assistant built around open-source AI.

🚀 GitHub Repository: https://github.com/GunjanPatil-cloud/Dev4

💡 The Idea

We spend too much time on repetitive digital tasks that don't require our full attention.

SlothMode AI is designed to make those tasks easier with three core features:

📁 Smart File Organizer — Preview and organize files into categories, with approval before changes and support for undoing operations.

📚 Study Material Summarizer — Turn PDF, DOCX, and text documents into concise summaries, key concepts, definitions, and revision questions.

📋 Lazy Task Planner — Convert a goal like “Prepare for tomorrow's DBMS viva” into small, manageable tasks.

The philosophy is simple: work smarter, automate the boring stuff, and save your energy for what matters.

🛠️ Built with Open-Source AI

The project uses:

Python for application logic and automation

Ollama for running AI models locally

Open-weight language models for summarization and task planning

Streamlit for the interactive interface

SQLite for local task storage

The goal is to make a useful AI assistant without depending on paid AI APIs for its core features.

🔓 Why Open Innovation Matters

For me, open-source AI is about more than saving API costs. It's about control.

🔒 Privacy: Documents can be processed locally instead of uploaded to a third-party AI service.

🔄 Flexibility: Models can be replaced, prompts adjusted, and the application customized to suit different needs.

💸 Cost-conscious automation: Local inference avoids per-request AI API charges, although hardware and electricity still have costs.

📴 Offline potential: After the model and dependencies are downloaded, core features can operate without an internet connection.

A hosted AI service may be faster or more capable for certain tasks, but local AI offers a different advantage: the ability to keep your tools and data under your control.

🦥 Why “Slow and Steady”?

Productivity isn't always about doing more things faster. Sometimes, it's about removing the small tasks that constantly interrupt us.

Imagine opening your laptop and finding your study notes summarized, your tasks organized, and your files easier to manage.

That's the experience I want SlothMode AI to work toward.

🚀 What's Next?

I'm working toward making the project more reliable, improving the user experience, and strengthening its local-first privacy and safety features.

I'd love to hear your thoughts:

What repetitive task would you automate first with a local AI assistant?

Explore the project, share feedback, and help make everyday productivity a little less exhausting.

🦥 Less busywork. More meaningful work.

OpenSource #AI #Ollama #Python #Productivity #BuildInPublic

PrivateLedger AI: Your Invoices, Your Device, Your Data 🔐

Gunjan — Sat, 17 Oct 2026 20:34:24 +0000

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

What I Built

Freelancers deal with invoices, receipts, payment records, and tax-related documents almost every day. Organizing them manually is tedious, and uploading them to an online AI service may expose sensitive client or financial information.

PrivateLedger AI is a privacy-first invoice and receipt organizer designed to run locally on your computer.

Drop in a batch of invoice images or PDFs, extract important information such as vendor names, dates, and amounts, review the results, organize the original files, and export verified records to CSV or Excel.

The idea is simple: make document management easier without requiring freelancers to send their financial documents to a cloud AI service.

Who would pay for it?

Freelancers, independent consultants, solo business owners, and small agencies that want to reduce administrative work while keeping their financial documents private.

Demo

GitHub repository: https://github.com/GunjanPatil-cloud/PrivateLedger-AI

Live demo: Not yet linked.

The application includes a demo mode using synthetic invoices, so its workflow can be explored without real financial documents.

Code

The project is open source under the MIT license.

Explore the source code, review the implementation, or run it locally:

Repository: https://github.com/GunjanPatil-cloud/PrivateLedger-AI

How I Built It

I built PrivateLedger AI around a local-first architecture:

Python + Streamlit: The application interface and workflow.

Tesseract OCR: Extracts text from invoice and receipt images.

PyMuPDF: Renders PDF pages for document processing.

Ollama + a local vision-language model: Helps extract structured information from documents on the user's machine.

Pandas: Handles the extracted records and exports.

SQLite: Optional local storage for extracted records.

The workflow combines OCR and local AI extraction, followed by a human review step. Users can correct the extracted information before exporting their records.

The project is designed so compatible local models can be changed through configuration rather than tying the entire application to a single proprietary AI API.

Why Does Open Innovation Matter?

For this project, privacy isn't just an extra feature. It is part of the reason the tool should exist.

Invoices can contain client names, addresses, payment details, tax identifiers, and other confidential information. A conventional cloud-based AI workflow may require sending that information to an external service.

By using open-source tools and a locally served model, PrivateLedger AI is designed to process documents on the user's own computer rather than upload their contents to a cloud AI provider.

Open innovation also gives this project three practical advantages:

Privacy and control

Users retain control over their documents and local processing environment. The application is designed not to send document data to a cloud AI API.

Freedom to change models

Ollama makes it possible to experiment with compatible models and choose one that fits the available hardware and extraction requirements.

A more sustainable side hustle

Local inference can avoid per-document cloud AI API charges. The trade-off is that users need compatible hardware, and model inference still consumes local computing resources.

The goal isn't to claim that open models are always more accurate or faster. It is to make a useful tool where control over data, flexibility, and reduced dependence on paid APIs are genuine advantages.

My Agent Session

Optional: Add a DevRelay agent session recording or link here if you have one.

My First User

The first milestone is to get PrivateLedger AI into the hands of a freelancer or independent consultant who regularly handles invoices.

I want to learn whether the tool saves them time, which fields need better extraction, and whether local processing is a meaningful reason for them to choose it over an online alternative.

I haven't included customer feedback or payment claims because these should come from a real user trial.

Prize Categories

Primary submission: Hacktoberfest Open-Source AI Challenge — Week 2: Side Hustle.

Potential additional category: Gemma, but only if I integrate and demonstrate Google's Gemma model in the project.

Thanks to the organizers and open-source community for encouraging small, practical AI projects that people can actually use.