This is a submission for the "Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady" (https://dev.to/challenges/hacktoberfest-week3-2026-10-19).
What I Built
I built CODENIVA AI — Quiet Queue, a privacy-first, open-source AI productivity assistant that transforms a messy collection of messages and tasks into a clear, prioritized daily action brief.
The goal is simple: spend less time sorting information and more time getting things done.
Quiet Queue classifies tasks into deadlines, replies, reviews, and lower-priority items. It highlights urgent deadlines, detects likely duplicates, and generates a structured summary.
Created during Hacktoberfest Week 3 in October 2026, this is a standalone experimental prototype under the broader CODENIVA AI vision.
Demo
"Watch the Quiet Queue demonstration" (https://github.com/CODENIVA-AI/quiet-queue/blob/main/assets/quiet_queue_demo.mp4)
The repository includes six synthetic sample records, example outputs, and a short offline demonstration animation.
The optional Gradio interface runs locally rather than on a publicly deployed server.
Code
GitHub Repository:
https://github.com/CODENIVA-AI/quiet-queue The public repository contains the source code, documentation, sample data, and automated tests.
How I Built It
The project uses scikit-learn, an open-source machine learning framework.
Its locally trained TF-IDF and logistic regression classifier categorizes short English and Arabic messages. A separate cosine-similarity process identifies potential duplicate items.
Explicit dates are prioritized using deterministic rules, and the results are exported as Markdown or JSON.
The software runs locally in Python without requiring paid AI APIs, commercial hosting, or cloud inference.
The prototype was developed with ChatGPT assistance. Its small synthetic training dataset limits accuracy, so human review remains essential.
Why Does Open Innovation Matter?
Open-source AI allows developers and users to inspect, understand, customize, and improve the system.
Unlike a closed cloud API workflow, Quiet Queue can process information locally without up private messages to an external AI service.
Its classification logic can be retrained, its examples expanded, and its components replaced by more advanced open models in future versions.
This approach supports privacy, transparency, low operating costs, and accessibility.
The Lazy Payoff
In the included synthetic demonstration, Quiet Queue processes six records, prioritizes an approaching deadline, and detects a duplicate pair.
All six automated tests passed during prototype validation.
The result is a repeatable task-organizing workflow. Real-world time savings have not yet been independently measured.
Quiet Queue does not automatically send emails, delete records, or make irreversible decisions.
About the Project
CODENIVA AI is a broader long-term vision for adaptable AI capabilities and intelligent automation. Quiet Queue demonstrates one small, practical component of that vision.
This prototype is released under the MIT License and does not include proprietary CODENIVA AI platform code.
BY DIRECTOR RASHED ALMAYYAS
POWERED BY CODENIVA AI