Freelancers using TkinterFreelancers using Tkinter
ProjectsPeople
Umaima Iqbal's avatar
Umaima Iqbal
Lahore, Pakistan
I build offline AI tools that make documents talk.
New to Contra
I build offline AI tools that make documents talk.
Cover image for AuraExtract — Intelligent Invoice &
AuraExtract — Intelligent Invoice & Receipt Data Extractor The extraction engine uses intelligent regex pattern matching that handles real-world invoice layouts — column-per-line PDF formats, inline tabular formats, and plain text documents. It detects 10 fields automatically and parses up to 20 line items per invoice. Supports PDF, TXT, and DOCX formats. Includes a raw text preview panel so users can verify exactly what the engine is reading. CSV export includes both the summary fields and full line items table — ready to open directly in Excel. Pure Python. Zero external dependencies beyond pypdf for PDF reading.
2
142
Cover image for AuraSort scans any folder and
AuraSort scans any folder and automatically sorts files into named subfolders by type — Documents, Images, Videos, Audio, Code, Archives, and more. Files are renamed to clean, consistent lowercase format. Every operation is logged live on screen as it happens. Built with a Dry Run mode so users can preview exactly what will move before anything is touched. Full undo restores every file to its original location with one click. An HTML report is generated after each sort showing every file moved, every category created, and total time taken. Pure Python. Zero external libraries. Works on any machine without installation.
2
146
Cover image for A fully offline document summarizer
A fully offline document summarizer built in pure Python. Uses TF-IDF scoring, position weighting, and Jaccard deduplication to extract the most important sentences from any PDF, DOCX, or TXT file — each labeled with a relevance percentage. The result looks like this: [1] [100% relevance] The algorithm achieved 94% accuracy on benchmark tests. [2] [81% relevance] Training was performed on 50,000 labeled samples. [3] [67% relevance] Results were validated using 5-fold cross validation. Supports PDF, Word, and TXT files. Saves summaries to your computer. Runs completely offline. No subscriptions, no API keys, no internet required.
1
140
Cover image for Built AuraChat v3.0 — a
Built AuraChat v3.0 — a fully offline Document Intelligence desktop app in pure Python. Users upload any PDF, Word, or TXT file and ask questions in plain English. The system returns cited answers with confidence scores instantly. Technical highlights: — Custom NLP engine using TF-IDF scoring + hybrid token overlap analysis — 1,700× faster indexing than baseline on 500-page documents — Multi-threaded processing — UI never freezes during heavy indexing — Supports PDF, DOCX, and TXT file formats — Zero external APIs — runs completely offline on the user's machine — 23 production-grade bugs identified and resolved before delivery This is not a demo. This is production-ready software built with clean architecture, full error handling, keyboard shortcuts, chat export, source citations, and confidence indicators
1
145
Tkinter(4)
Alessandro Federici's avatar
Alessandro Federici
proBologna, Italy
AI & Automation Developer, I'll build your App / Automation
2x
Hired
5.0
Rating
14
Followers
AI & Automation Developer, I'll build your App / Automation
Cover image for AF Speech: Offline AI Desktop App Development
AF Speech: Offline AI Desktop App Development
0
21
Cover image for AI Voice Booking Agent
AI Voice Booking Agent
0
20
Cover image for AI Cold Outreach Platform
AI Cold Outreach Platform
0
7
Cover image for Business Analyzer (AI Report)
Business Analyzer (AI Report)
0
5
Tkinter(1)
Arslan Khan's avatar
Arslan Khan
Peshawar, Pakistan
AI Automation Architect | n8n · LLM Agents -CRM Tools
New to Contra
AI Automation Architect | n8n · LLM Agents -CRM Tools
Cover image for Studio CGI Car Photography —
Studio CGI Car Photography — Without the $30K Production Budget BMW and Mercedes-tier car campaigns use CGI studios that cost $5,000-$30,000 per shoot and take weeks — matched reflections, physically accurate tyre-contact shadows, studio floor lighting, all hand-built by render artists frame by frame. This engine reproduces that exact physical process — real reflection geometry, real per-tyre contact shadows, real lighting match — but it runs in seconds, not weeks, because it's built as a rendering pipeline, not a filter. This isn't a background-remover with a blur effect under it. It's the same physics those studios use, automated.
0
51
Cover image for KPPSC Prep Pro – First
KPPSC Prep Pro – First AI-Integrated Self-Healing MCQ Engine for Pakistan's Largest Exam
0
58
Cover image for Apex — Automated B2B Cold
Apex — Automated B2B Cold Outreach Pipeline Built a fully autonomous B2B lead generation and cold outreach system that runs daily with zero manual input. The pipeline scrapes HR consulting firms from Google Maps via SerpApi, crawls each business website using Crawl4AI to extract contact emails, filters duplicates against a Google Sheets master log, generates personalized HTML cold emails with randomized send delays to mimic human behavior, and logs every sent lead with timestamp and sender account. Results: 400+ targeted emails sent across 3 days to verified HR consulting firms across New York — fully automated from lead discovery to inbox delivery.
0
62
Cover image for Understood. We are keeping it
Understood. We are keeping it strictly professional and consistent with your master tagset. Here is the draft for MediBook to add to your Contra profile. Contra Project Entry: MediBook Healthcare Platform Project Title: MediBook Healthcare Appointment Management Platform Role: Lead Systems Engineer & AI Automation Architect Project Description: I architected and deployed MediBook, a comprehensive healthcare appointment management ecosystem. The platform facilitates the end-to-end appointment lifecycle, from patient registration and secure booking to administrative approval and automated patient communication. I engineered an automated workflow that handles approval notifications and appointment reminders, significantly reducing manual follow-up overhead for clinics while enhancing patient experience. The architecture integrates robust authentication with automated backend operational logic." Skills: AI Automation, Automation, Software Development, Systems Architecture, Backend Development, API Integration, Workflow Engineering Tools: n8n, Python, Gmail API, PostgreSQL, Supabase, External API Integration
0
70
Tkinter(1)
Vaibhav Mishra's avatar
Vaibhav Mishra
Faridabad, India
A Professional Full Stack Developer
A Professional Full Stack Developer
Cover image for Face Recognition and Verification System Development
Face Recognition and Verification System Development
1
1
Cover image for OCR Python Script Development
OCR Python Script Development
1
5
Cover image for Rice Grain Species Classification using Machine Learning
Rice Grain Species Classification using Machine Learning
1
3
Placeholder project card media
View more →
Tkinter(2)
Kseniya Mikhno's avatar
Kseniya Mikhno
Brisbane City QLD 4000, Australia
Python Developer | IoT, ML & Full Stack
New to Contra
Python Developer | IoT, ML & Full Stack
Cover image for Built a desktop application for
Built a desktop application for managing repair jobs, designed for small businesses that need to track incoming repairs, parts, costs, and customer information in one place. The application features a clean interface for logging new repair jobs, tracking their status through completion, managing customer records, and generating reports. All data is stored in a SQL database with full CRUD operations. Key features include job intake and status tracking, customer and parts management, cost calculation and invoicing, and reporting for business insights. Built with Python for the application logic and UI, and SQL for persistent data storage.
1
41
Cover image for Developed and integrated a machine
Developed and integrated a machine learning system for geospatial mineral exploration analysis in collaboration with an industry partner. The system processes terrain and geological data to identify potential mineral deposits. The project involved building data pipelines to ingest and clean geospatial datasets, training machine learning models to recognize patterns associated with mineral deposits, and creating visualizations of the analysis results. Key features include automated geospatial data processing, machine learning model training and evaluation, integration with industry partner workflows, and visual output of exploration analysis results. The tech stack included Python for data processing and model development, SQL for data management, and machine learning libraries for predictive analysis.
1
29
Cover image for Developed an IoT-based communication system
Developed an IoT-based communication system that converts web-submitted text messages into Morse code signals transmitted via LED using Raspberry Pi GPIO controls. The goal was to build a system that bridges web-based text input with physical hardware output, demonstrating IoT communication principles through a practical Morse code implementation. I built a web interface where users submit text messages. The backend processes the text, converts each character into its Morse code equivalent, and sends the signal pattern to Raspberry Pi GPIO pins. An LED physically blinks the Morse code in real time. Key features include a web-based text input interface, real-time text-to-Morse-code conversion, Raspberry Pi GPIO integration for LED signal output, and a full-stack architecture connecting the web layer to the hardware layer. The tech stack included Python for backend logic and GPIO control, Raspberry Pi for hardware interfacing, and web technologies for the user-facing input form.
1
32
Cover image for Developed a web-based job tracking
Developed a web-based job tracking system for a waterproofing business, allowing clients to monitor project progress through a secure web portal accessed via unique QR codes. The waterproofing business needed a way for their clients to track the status of ongoing projects without constant phone calls or emails. They wanted something simple, accessible, and secure. Built a full-stack web application where each job gets a unique QR code. Clients scan the code and are taken to a secure portal showing real-time progress updates on their project. The backend handles job management, status updates, and client authentication. Key features include QR code generation linked to individual jobs, a secure client portal for real-time project tracking, an admin dashboard for managing jobs and updating statuses, and a web-based interface accessible from any device. Python for backend logic, SQL for data management, and web technologies for the client-facing portal.
1
34
Tkinter(1)
Prajjwal Barmaiya's avatar
Prajjwal Barmaiya
Delhi, India
punctual, motivated, hardworker, Quick Learner
punctual, motivated, hardworker, Quick Learner
Cover image for Automatic Attendance System with Face Recognition
Automatic Attendance System with Face Recognition
1
4
Cover image for RISC-V Based Single-Cycle Core Design
RISC-V Based Single-Cycle Core Design
1
4
Cover image for Music-Player-Using-HTML-And-CSS
Music-Player-Using-HTML-And-CSS
1
7
Placeholder project card media
View more →
Tkinter(1)
Aaron Segiel's avatar
Aaron Segiel
Boca Raton, USA
AI engineer and Web Developer
AI engineer and Web Developer
Cover image for AI Code Reviewer Application Development
AI Code Reviewer Application Development
0
27
Cover image for Web Scraping for News Titles
Web Scraping for News Titles
0
15
Cover image for CIFAR-10 Image Classification with CNN
CIFAR-10 Image Classification with CNN
0
13
Placeholder project card media
View more →
Tkinter(1)