Safari extension for iPhone, iPad & Mac - automatic tracker removal, smart redirects, source credibility warnings (powered by CRED-1), and browser tweaks. 100% on-device, zero data collection. Universal purchase with iCloud sync.

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"

This repository provides scripts and workflows for translating fact-checking datasets and automating claim classification using large language models (LLMs).

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

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

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 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.

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.

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

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.

Novel multimodal architecture for detecting such misinformation by explicitly modeling the consistency between visual content, textual claims, and external factual knowledge.

Adventure Guardian AI is a unified safety intelligence system designed to protect adventure travellers in India. It verifies trek information, analyzes health risks, and detects fraud using AI-powered vision, geodata, weather intelligence, and pattern analysis. By combining truth, health, and fraud assessments, it generates a single Verified Trek S

AI-powered fake news detection system using advanced NLP, fact verification, and source reliability analysis. Built with Next.js 14, featuring real-time credibility assessment, comprehensive RESTful API, and professional dark/light mode interface for combating misinformation.

Flask web app for explainable misinformation analysis using live search evidence, source hints, and structured verdicts.

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.

Media Literacy System powered by AI - Analyze news for bias and manipulation.