DEV Community: Bhumika Sudarshani

Van-to-Quote

Bhumika Sudarshani — Fri, 16 Oct 2026 19:50:17 +0000

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

What I Built

Van-to-Quote is a local app that turns a tradesperson's spoken job notes into a priced PDF quote.

Plumbers, electricians and other tradespeople finish a job and then spend an evening typing up quotes. Cloud quoting apps charge a monthly fee, need a signal, and keep customer data on someone else's server. With Van-to-Quote you hold a button and say "replaced two radiators, three hours, forty meters of pipe". A draft quote appears with the right items, quantities, labour and VAT. You fix anything that looks off, then download the PDF.

Who would pay: solo tradespeople and small trade businesses who quote on site, often with poor signal. Because there is no per-quote cost, it could be sold as a one-time license or a small flat fee.

Demo

See the demo GIF and screenshots in the README: [PASTE REPO LINK]

Code

bhumikasudarshani-cmd / van-to-quote

Van-to-Quote 🔧

Talk about a job, get a priced PDF quote. Runs fully offline once models are downloaded.

Setup

Install Ollama (https://ollama.com), then: ollama pull qwen2.5:7b (or qwen2.5:3b for small laptops)
pip install -r requirements.txt
Edit prices.json with your business name, rates, VAT and price list
python app.py and open http://localhost:5000

Mic access works on localhost. To use from a phone on your wifi, serve over HTTPS or use the text box.

How it works

Whisper (faster-whisper) transcribes -> a local LLM extracts items, quantities and hours as JSON -> your own price list supplies every price and all maths is plain code. The model never makes up a price. Config via env vars: LLM_MODEL, WHISPER_MODEL, OLLAMA_URL.

View on GitHub

How I Built It

The whole pipeline runs on a laptop:

faster-whisper (open-source speech recognition) transcribes the recording.
Qwen2.5 3B, running locally through Ollama, extracts the customer, items, quantities and labour hours as JSON.
Plain Python matches items against the tradesperson's own prices.json, calculates VAT and totals, and builds the PDF with ReportLab.
A small Flask web page shows an editable draft. Items that aren't in the price list are flagged orange so a price can be set by hand.

The key design choice: the model never sets a price. It only decides what was done. The price list and ordinary code decide what it costs. A small model can mishear a number, but it can't invent a price or get the maths wrong, and every mistake is visible on the draft screen before anything is sent.

I tested the full flow end to end on my own laptop with spoken job descriptions.

Why Does Open Innovation Matter?

Private by design. Customer names, addresses and prices never leave the laptop. A cloud API can't offer that.
Works with no signal. Basements, new builds and rural jobs are exactly where tradespeople quote.
Costs nothing per quote. There is no API bill, so a flat price for the tool still leaves real margin however many quotes someone writes.
Swappable and adaptable. Changing the model is one setting, and the price list and prompt are plain files. A plumber, a painter and an electrician can each have their own setup, and nobody's pricing or terms can change under them.

Verdant: A Local AI That Pays You in Swag to Go Outside is clear and says what it does, and it’s my top pick.

Bhumika Sudarshani — Sun, 11 Oct 2026 14:40:30 +0000

What I Built

Verdant is a quest master that runs on your own laptop and wants you to close it.

An open-weight AI writes you outdoor quests based on the season and the weather, like a 3 km foliage stroll with a leaf to photograph. You go outside and do it. Back home, Verdant checks your GPS track and your photo, and if both pass, it issues a signed voucher. A sponsor, such as a running shop or an eco brand, pastes the voucher into the Verdant Sponsor Portal, sees at once that it’s genuine, and knows which reward to ship: a sticker pack, a finisher medal, or a swag box.

It’s for people who need a small push to start: new walkers, beginner runners, and anyone whose daily steps are mostly to the fridge. The screen is only for getting a quest and claiming the reward, and the real experience happens outside.

Demo

A note on testing: I wasn’t able to record a real outdoor walk before the deadline, so the route in this demo is a simulated GPS track generated with a small script. It tests the verification logic, but it isn’t a real outdoor test. The Sponsor Portal ran locally for these screenshots, and the repo includes a render.yaml for deploying it. Taking Verdant outside is my next step.

The quests Gemma generated
PASS route and PASS photo in the terminal
The Sponsor Portal showing VALID
The same voucher showing ALREADY REDEEMED
An edited voucher (bronze changed to gold) showing INVALID
Code

bhumikasudarshani-cmd / verdant

verdant

View on GitHub

It’s one Python file for the quest master and one for the sponsor portal. Neither needs any extra packages, so a beginner can read all of it in ten minutes.

How I Built It

Verdant has four parts, and only two of them need AI.

Quests (Gemma, running locally). Verdant asks Gemma 3 through Ollama for quests in JSON, based on the user’s level, the season and the weather. If the model isn’t available, built-in quests take over, so the tool still works on a trail.
Route check (plain code, on purpose). A GPX track is checked for total distance, human pace and impossible jumps. A “5K run” averaging 45 km/h is a car, and a few lines of maths catch that more reliably than an AI model would. Using AI only where it helps was a real lesson for me.
Photo check (Gemma’s vision, locally). For quests like “a fallen autumn leaf”, the same Gemma model looks at the photo and answers yes or no. One model does both jobs, and the photo never leaves the machine.
Signed vouchers and the Sponsor Portal. A passed quest produces a voucher signed with HMAC-SHA256. The portal, a small standard-library Python server, verifies the signature, shows the reward, and blocks the same voucher from being redeemed twice. If someone edits a voucher to upgrade bronze to gold, the signature no longer matches and the portal says INVALID.

Only a hash of the track goes into the voucher, so sponsors never see where you walked.

What went wrong along the way: Gemma wrote long paragraphs for the photo instruction at first, so the photo check kept answering “No”. I fixed it by shortening the subject before sending it to the model and by asking Gemma for short photo subjects in the first place. I also hit install problems and a server that wouldn’t start. [Add one or two more in your own words.]

Why Does Open Innovation Matter?
It works without signal. Trails are where connectivity disappears. Because the model runs locally, quests and checks work in the woods.
Your location stays yours. GPS tracks and photos of your surroundings are very personal. They are processed on your own machine, and a sponsor only ever receives a signature and a hash.
I could swap the brain in one line. I started with one model for text and another for photos, then moved to a single Gemma model by changing two settings. With a closed API, a price change or deprecation could end the project.
It costs nothing to run. That matters if outdoor challenges are meant to be free for beginners and affordable for small local sponsors.
Sponsors can read the rules. The verification logic is open, so a sponsor can see exactly how a voucher was earned instead of trusting a black box.

Limitations: Outdoor testing was limited to a simulated route. Vouchers use a shared secret in this prototype, so public-key signatures are the next step. The “already redeemed” list lives in memory and resets when the server restarts, so a real version needs a database. The sponsors in the code are placeholders.

Elixpo: An Open-Source Ecosystem That Started as a College Initiative (and Its Blogging Platform You Can Contribute To)

Bhumika Sudarshani — Mon, 05 Oct 2026 16:04:07 +0000

What is Elixpo?

Elixpo began in 2023 as a small college initiative. Today it is an open-source ecosystem of 9+ interconnected tools for creating, writing, drawing, searching and building on the web, shaped by 45+ contributors around the world.

The belief behind it is simple: AI and great software should be open, ethical and free for everyone. Every tool is open source and free to use, with no paywalls, no premium tiers and no sign-up walls on the public tools.

A few numbers from the journey so far:

9+ open-source projects built and deployed
45+ global contributors
20+ hackathons participated in
Part of programs like GSSOC, Pollinations.AI and OSCI
Recognized by MS Startup Foundations with funding in 2024

The ecosystem at a glance

Tool	What it does
Elixpo Blogs	A rich, modern writing and publishing space
LixSketch	A hand-drawn style whiteboard for ideas and diagrams
Elixpo Search	Fast, AI-assisted search
Elixpo Accounts	One identity (SSO) across the ecosystem
lixrl	A URL shortener
Portfolios	Personal pages to showcase your work

Some tools, like Elixpo Art and Elixpo Chat, are still under development.

The people behind Elixpo

Elixpo is made by people, in the open. 45+ contributors have shaped these tools, with a small core team steering the way:

Ayushman Bhattacharya, Founder & Lead (@Circuit-Overtime)
Vivek Yadav, Lead Co-Dev (@ez-vivek)
Anwesha Chakraborty, Core Maintainer (@anwe-ch)

Spotlight: Elixpo Blogs

Elixpo Blogs (LixBlogs) is a free, open-source blogging platform for creators, developers and teams. Live at blogs.elixpo.com.

What you get:

Rich block editor with 20+ block types: code, LaTeX math, Mermaid diagrams, tables, embeds, sub-pages
AI writing assistant: press Space on an empty line to generate text and images
Real-time collaboration with live cursors and presence
Organizations and teams, with roles and collections
Auto-save and cloud sync, so drafts are never lost
Media uploads auto-compressed to WebP
Library and bookmarks for saving and organizing posts

Under the hood

For the engineers reading this, here is the stack:

Frontend: Next.js 15 and React 19, with the editor built on BlockNote
Real-time sync: Yjs (CRDT) over WebSockets to Cloudflare Durable Objects
Edge infrastructure: Cloudflare Pages and Workers, D1 for the database, KV for caching
Auth: Elixpo Accounts (SSO)

The editor is also published separately as @elixpo/lixeditor on npm, plus a VS Code extension, so you can drop the same editor into your own React app:

npm install @elixpo/lixeditor @blocknote/core @blocknote/react @blocknote/mantine

Run it locally

npm install
npm run dev

Then open http://localhost:3000. Create a .env.local first with your development credentials. See the README for the details.

Everyone is welcome to contribute

This is the part I care about most. No matter your experience level, you are welcome here.

You don't need to start with a big feature. Some real ways to help:

Fix a bug or improve the editor UX
Improve docs and the README
Test the platform and report issues
Pick up a good first issue
Suggest features you'd want as a writer

Repo: https://github.com/elixpo/blogs.elixpo

A quick note on Hacktoberfest: in 2026 it moved away from counting pull requests and now focuses on open-source AI events, so I'm not promising swag for PRs. What I can promise is real code review, real feedback, and a project you can point to in your portfolio.

Please read CONTRIBUTING.md and the Code of Conduct before you start, and comment on an issue before working on it so we avoid duplicate effort.

Let's build it together

Elixpo grew from a college project into a community because people showed up and built things together. If you've been waiting for a sign to try open source, this is it.

Which feature would you want in a blogging platform? Tell me in the comments.