InkFlow: The Adaptive Writing Twin & Anti-AI-Slop Engine
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle What I Built We are living through a time when AI-generated writing is becoming increasingly common, but much of it sounds remarkably similar. When people use generic AI assistants to polish emails, academic papers, or technical reports, their original writing style can get replaced by repetitive buzzwords,…
Title: InkFlow: Adaptive Writing Twin & Anti-AI Slop Engine
In the era where AI-generated writing is pervasive, a notable issue emerges: authentic voices are often overshadowed by generic, repetitive language. To address this, the InkFlow writing assistant was developed. Its primary mission is to refine written content while maintaining the author's unique style.
InkFlow operates on four core functionalities. The first is Personal Style Genome, a two-minute exercise that establishes an eight-dimensional profile of the user's writing style. This includes formality, sentence structure variability, vocabulary diversity, clause complexity, and punctuation habits.
The second function is AI-Slop Detection, which identifies and highlights cliché-laden phrases that typically render drafts unoriginal. The third function is a four-stage rewrite pipeline. This includes text generation or transformation, elimination of unwanted stylistic patterns, semantic consistency check, and a grammar pass, all designed to respect the author's punctuation preferences.
The fourth function is Adaptive Style Learning. This feature monitors writing patterns across sessions and incorporates recurring stylistic preferences without overreacting to individual edits.
The Side Hustle model of InkFlow is a freemium approach. The free tier offers basic features such as 1,500 words per day, one personal Style Genome profile, AI-slop highlighting, and the Humanize Studio. The Pro Tier, priced at ₹39 per month, provides unlimited daily words, multiple writing profiles, and priority access to open-weight models via an integrated Razorpay checkout that supports various payment methods.
The Live Web Application for InkFlow can be accessed at https://ink-flow-twin.vercel.app. The Backend API is available at https://inkflow-backend-73hf.onrender.com. A demo video is hosted on Google Drive at drive.google.com.
Explore features such as the Humanize Studio, which allows users to refine drafts by identifying and rectifying common AI-style clichés. The Two-Minute Voice Calibration helps users create their unique Style Genome. The Sentence Cadence Analytics tool examines sentence length variation across paragraphs. The Direct AI Writer feature enables users to draft and refine content, and the Code GitHub Repository is located at https://github.com/SoumyaGhosh2006/InkFlow.
The project employs a modular full-stack architecture. The backend is built on FastAPI (Python 3.11+), utilizes MongoDB with Motor for asynchronous access, Groq for inference, Pydantic v2, Razorpay integration, Sentry for tracing, and Pytest for testing. The frontend is constructed with React 19, TypeScript, Vite, Tailwind CSS, Framer Motion, Zustand, Radix UI, Lucide icons, and Firebase Authentication.
The repository includes the entire writing pipeline, style calibration, authentication, and subscription workflow implementation.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
