Devpost
Participate in our public hackathons
Devpost for Teams
Access your company's private hackathons
Grow your developer ecosystem and promote your platform
Drive innovation, collaboration, and retention within your organization
By use case
Blog
Insights into hackathon planning and participation
Customer stories
Inspiration from peers and other industry leaders
Planning guides
Best practices for planning online and in-person hackathons
Webinars & events
Upcoming events and on-demand recordings
Help desk
Common questions and support documentation
An edge-optimized, multilingual NLP architecture delivering 99%+ accuracy via lightweight Soft-Voting Ensembles, completely bypassing the latency, API costs, and hardware bottlenecks of heavy LLMs.
XLM-RoBERTa fine-tuned for multilingual toxicity detection across multiple languages. Achieves Mean ROC-AUC of 0.9918 with LIME-based explainability and an interactive Gradio demo.
A cross-lingual AI moderator detecting Hindi/English hate speech. Powered by an mDeBERTa-v3 PyTorch pipeline with a 94.4% F1-Score, connected to a live, real-time Streamlit UI.
An AI-powered NLP system that analyzes news titles and content to detect fake or misleading information with high accuracy, helping combat misinformation in real time.
A production-ready NLP platform solving disaster detection, fake news classification, and multilingual toxicity analysis — live inference, batch predictions, and outputs for NeuroLogic '26 challenges.
Toxic Trap AI is a high-speed moderation engine built to catch multilingual hate speech that basic filters miss. It uses a dual-model pipeline to trap toxic nuances in English, Hindi,etc with zero lag
This project classifies news articles as real or fake by combining title and text. It uses TF-IDF features and a Logistic Regression model to make accurate predictions.
Detecting toxic content in multilingual posts using ML.
An easy-to-use library designed to help developers combat online harassment and mitigate bias by identifying threats, insults, and identity-attacks across multiple languages
REMOVING TOXICITY
Built an NLP-powered model that detects toxic comments across multiple languages in real time, helping create safer online spaces by flagging harmful content with high accuracy and scalability.
SemantiX is a multilingual toxicity detection system using XLM-RoBERTa to classify Hindi and English text in real time, enabling scalable and accurate content moderation.
Detecting toxic comments across Hindi, English, and code-mixed text — because harmful speech doesn't stay in one language.
This project focuses on building a robust Natural Language Processing (NLP) model to classify news articles as Real or Fake.
Fighting misinformation with AI—detecting disasters, debunking fake news, and filtering toxicity across languages
An intelligent NLP system for detecting toxic content in multilingual conversations
Multilingual toxic comment classifier using XLM-RoBERTa achieving ROC-AUC of 0.9922, detecting toxic content across Hindi and English text for scalable cross-lingual content moderation.
**"Detecting toxicity across languages using MuRIL — because hate doesn't speak just one language."**
Fake news detector using RoBERTa achieving 99.87% accuracy by analyzing news titles and article content to automatically identify misleading information at scale.
Multilingual multi-label toxic comment classification for global community moderation.
This project solves three NLP classification challenges using a simple and effective machine learning approach.
Real-time disaster tweet classifier using BERTweet achieving Macro F1-Score of =0.8955 to help first responders identify critical information from social media during emergencies.
CoreDefance focuses on speed, simplicity, and accessibility.
Disaster Tip Classifier is a beginner‑friendly Python project that instantly identifies disaster types from text . Built for hackathon deployment, it promotes awareness through simple logic
1 – 24 of 26
