Local Invoice & Receipt Sorter for Freelancers — Open-Source AI Side Hustle

Viraj Radadiya — Thu, 15 Oct 2026 05:07:11 +0000

What I Built
I built LocalFolio, an offline-first invoice and receipt organizer specifically designed for freelancers, independent contractors, and sole proprietors.

Handling client receipts and expense invoices is tedious, manual, and privacy-sensitive. Freelancers often hesitate to upload sensitive financial documents containing client names, tax IDs, and bank details to cloud-based proprietary APIs. LocalFolio solves this by running entirely on the user's local machine. It ingests messy folders of PDFs, screenshots, and scans, uses a local vision-language model to extract structured metadata (vendor, date, total amount, category, and tax status), and automatically sorts them into clean, structured folder hierarchies with a fully searchable SQLite ledger.

Demo

(Link to video demo showing drag-and-drop receipt ingestion, local extraction, and auto-sorting in action)

Code
You can check out the complete project repository on GitHub:
LocalFolio GitHub Repository

Python

Core local inference pipeline snippet using Ollama and Llama 3 Vision

import json
from pathlib import Path
from ollama import chat

def process_receipt(image_path: Path) -> dict:
prompt = """
Extract the following invoice details in strict JSON format:
- vendor_name
- date (YYYY-MM-DD)
- total_amount
- currency
- category
"""
response = chat(
model='llama3.2-vision',
messages=[{
'role': 'user',
'content': prompt,
'images': [str(image_path)]
}],
format='json'
)
return json.loads(response['message']['content'])
How I Built It
LocalFolio is built around modern open-source AI tools and frameworks:

Open-Weight Models: Powered by Llama 3.2 (3B Vision) running locally via Ollama, allowing high-accuracy multi-modal OCR and structured information extraction without relying on external cloud endpoints.

Agent Harness & Framework: Built using Python, LangChain for structuring extraction prompts, and Pydantic for rigorous data validation.

Local Storage & UI: A lightweight desktop GUI built with Streamlit backed by a local SQLite database and local file system operations to organize documents directly in the user's chosen directory.

Why Does Open Innovation Matter?
Open innovation was non-negotiable for LocalFolio due to three core pillars:

Absolute Data Privacy: Financial invoices contain sensitive PII, proprietary client names, and banking details. Running open-weight models locally ensures that confidential client data never leaves the freelancer's laptop, satisfying strict client confidentiality agreements.

Zero Recurring Infrastructure Costs: Cloud-based OCR and proprietary vision APIs charge per request, which would quickly eat into thin freelancer margins or require a burdensome subscription model. Local inference costs $0.00 per scan, making the side hustle sustainably profitable.

Customizability & Fine-Tuning: Generic invoice parsers often fail on regional tax formats (like GST/VAT structures or niche local currencies). Open models allowed custom prompt engineering and local few-shot tuning specifically tailored to freelance expense categories.

My Agent Session
During the development of LocalFolio, I used DevRelay to record and track my agentic debugging and coding sessions:
View my DevRelay Agent Session

My First User
I tested LocalFolio with my friend Sarah, a freelance graphic designer who spends hours every month sorting through messy PDF invoices and mobile snapshots of tax receipts.

Her Feedback: She loved that she didn't have to create an account, configure API keys, or worry about uploading confidential client retainer agreements to a third-party server.

What she asked for next: She requested an automated export feature to generate a CSV summary sheet formatted specifically for her annual tax filing software.

Would she pay? She stated she would gladly pay a one-time fee of $29 for a polished desktop installer so she never has to manually categorize receipts again.

Prize Categories
Open-Source AI / Local Inference

Developer Productivity & Tools

NutriMate – Local AI Meal Planner for My Roommate's Severe Allergies

Viraj Radadiya — Sun, 04 Oct 2026 08:46:18 +0000

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

What I Built

I built NutriMate for my roommate, Alex, who suffers from severe, multi-ingredient food allergies (peanuts, gluten, and dairy).

Problem: Planning daily meals was a constant stress for Alex. Commercial recipe apps often miss cross-contamination risks or hide allergy filters behind expensive paywalls. Moreover, Alex didn't feel comfortable uploading sensitive health and dietary preferences to public AI cloud platforms.

Solution: NutriMate is a fully offline, local AI-powered meal assistant. It analyzes available pantry items, cross-checks every ingredient against Alex's strict allergy profile, and generates personalized, safe weekly meal plans and grocery lists in seconds.

Demo

Live Demo / App: https://nutrimate-demo.example.com

Code

{}

How I Built It

NutriMate is powered entirely by open-source AI infrastructure running locally on a standard laptop:

LLM / Open-Weights: Llama 3.2 (3B-Instruct) running locally via Ollama for high-speed, zero-latency meal reasoning.
Agent Framework: LangChain to enforce strict system guardrails, structured JSON output formats, and deterministic allergy verification.
Backend & UI: Python FastAPI for local endpoint management and Streamlit for a clean, user-friendly dashboard.

Why Does Open Innovation Matter?

Using open-source AI wasn't just an alternative—it was the only option that truly solved Alex's core concerns:

Complete Data Privacy: Alex's medical allergy records and daily eating habits remain 100% on their personal laptop. No data ever touches a third-party server.
Offline & Reliability: It runs with zero internet connection. Whether cooking in a basement apartment or traveling without WiFi, NutriMate works instantly.
Zero Operating Cost: Running open-weight models locally eliminates expensive API subscription fees, making it free forever.
Deterministic Behavior: Open-source frameworks allowed us to fine-tune system prompts and temperature settings to ensure the model never hallucinates unsafe ingredients.

User Feedback

Here is what Alex said when I installed NutriMate on their laptop:

"I used to spend hours scanning ingredient lists and overthinking dinner. NutriMate gave me complete peace of mind because I know my data stays on my laptop and every recipe is 100% safe for me to eat. It’s genuinely a lifesaver!"

Prize Categories

Main Challenge: Build for a Friend

DEV Community: Viraj Radadiya

Local Invoice & Receipt Sorter for Freelancers — Open-Source AI Side Hustle

Core local inference pipeline snippet using Ollama and Llama 3 Vision

NutriMate – Local AI Meal Planner for My Roommate's Severe Allergies

What I Built

Demo

Code

How I Built It

Why Does Open Innovation Matter?

User Feedback

Prize Categories