Safari extension for iPhone, iPad & Mac. Strip tracking from every link, watch YouTube in Picture-in-Picture, force links to open in Safari (not the installed app), and get Source Credibility warnings powered by CRED-1. 100% on-device, zero data collection.

Towards Robust Fact-Checking: A Multi-Agent System with Advanced Evidence Retrieval

FailSafe: An autonomous fact-checking framework leveraging Multi-Agent LLMs and Structured Argumentation Graphs (SAG) to verify claims with deep-web retrieval and reasoning.

Code associated with the NAACL 2025 paper "COVE: COntext and VEracity prediction for out-of-context images"

Code associated with the preprint: "M4FC: a Multimodal, , Multilingual, Multicultural, Multitask real-world Fact-Checking Dataset"

This repository contains the code to reproduce the work "Automated Fact-Checking in Brazilian Portuguese: Resources and Baselines", accepted at STIL 2025.

The Reality Button is a Chrome extension that provides on-demand, AI-powered verification of selected text anywhere on the web. It sends the highlighted content through a private Node.js proxy to Google’s Gemini 2.5 Flash model, returning a grounded, concise assessment of factual accuracy with clear explanations.

TRINETRA — Intelligent Threat & Misinformation Detection Platform

Machine Learning and NLP system for detecting social media misinformation and prioritizing high-risk content using risk-based optimization.

Tathya (तथ्य, "truth") is an Agentic fact-checking system that verifies claims using multiple sources including Google Search, DuckDuckGo, Wikidata, and news APIs. It provides structured analysis with confidence scores, detailed explanations, and transparent source attribution through a modern Streamlit interface and FastAPI backend.

🔍 ABCheckers 💬 is a data-driven project that analyzes Twitter discourse to uncover misinformation around 🇵🇭 inflation and the weakening peso, empowering users with contextual insights.

An advanced AI-powered fake news detection system that verifies text, images, and social media posts using Gemini AI, FastAPI, and Next.js. Includes a modern web interface, a lightweight Streamlit app, and a Chrome extension for real-time fake content detection. Built to combat misinformation with explainable AI results and contextual source links.

An Agentic AI system for Deepfake Detection & Media Authenticity Verification. Features autonomous model routing, an ensemble of 6 specialized neural networks, and advanced bias correction mechanisms.

OpenSiteTrust is an open, explainable, and reusable website scoring ecosystem

TruthLens is a multimodal browser plugin that detects misleading thumbnails, clickbait titles, and low-trust video patterns, then explains, filters, and helps report suspicious content using probabilistic scoring, user feedback, and adaptive AI.

Fake News Detection System, based on Machine Learning & Deep Learning, trained on 44,000+ news articles using TF-IDF, Logistic Regression, Decision Tree, Random Forest, CNN, and LSTM, achieving up to 99.76% accuracy.

A full-stack web application that detects fake news and misinformation in real time using Natural Language Processing (NLP), a TF-IDF Vectorizer, and a Logistic Regression machine learning model.

Forensic AI platform that detects manipulation, bias, and psyops in news articles. FastAPI backend, Chrome extension, React Native app, and website — powered by xAI Grok + Tavily.

AI-powered multi-agent fact-checking system for WhatsApp Web — built with LangChain, Claude API, RAG, and a Chrome extension to detect misinformation, scams, and dubious claims in real-time.

This project implements a complete NLP pipeline for Persian tweets to classify topics and detect fake news. Using a Random Forest classifier, it compares tweet content with trusted news sources, achieving 70% accuracy in fake news detection.