Project Info
Inspiration
Everyone on the internet today knows the struggle of staying rooted in the truth, but nobody ends up taking the extra time to verify or fact-check everything they see online. We wanted a browser extension that would allow people to check what they see online quickly and easily, so everyone could be more encouraged to double-check what they react to.
What it does
Our extension allows you to highlight any text and immediately get deep research about what you read, complete with sources. Additionally, you can open the extension to get access to four buttons. One button checks the entire article to see if the general information is correct. Another button allows you to take a screenshot of an image to see if it is AI-generated. Yet another button allows you to scan the article you are looking at to see if it was written by AI. Finally, the last button gives you information about what you are reading, letting you know if it is biased and how generally credible its reputation is.
How we built it
We built this extension using the standard Chrome extension framework using JavaScript and HTML, using Git for version control. We incorporated multiple APIs into the extension: Groq, Sapling, and Sightengine.
groq-is-this-true
A Chrome extension for fact-checking text and detecting AI-generated images.
Features
📝 Fact Checking
- Select text on any webpage to fact-check it using Groq AI
- Get instant verification with sources
🖼️ AI Image Detection
- Capture and analyze screenshots to detect AI-generated images
- Uses Sightengine's AI detection API
- Interactive cropper to select specific areas of the page
- Visual confidence indicators
Setup
1. Install Dependencies
npm install
2. Build the Extension
npm run build
3. Configure API Keys
- Load the extension in Chrome (Developer mode)
- Click on the extension icon and go to Options
- Enter your API credentials:
- GROQ API Key: Get from console.groq.com
- Sightengine API User & Secret: Get from sightengine.com
Usage
Fact Check Text
- Select any text on a webpage
- Click the extension icon
- Click "📝 Fact Check" button
- View the fact-check results and sources
Detect AI Images
- Click the extension icon
- Click "🖼️ AI Detect" button
- Click "📸 Capture Screenshot"
- Draw a rectangle around the image you want to analyze
- View the AI detection results with confidence score
How It Works
Screenshot Capture Flow
- User clicks "Capture Screenshot" in the popup
- Content script (
selection.js) creates an overlay with crosshair cursor - User draws a rectangle to select the area
- Screenshot is captured using
chrome.tabs.captureVisibleTab - Image is cropped to the selected area
- Cropped image is sent to Sightengine API for AI detection
- Results are displayed in the popup
Technologies Used
- Groq AI: For fact-checking text content
- Sightengine API: For AI-generated image detection
- Cropper.js: For interactive screenshot selection
- Chrome Extension APIs: For browser integration
Development Ideas
- agentic
- automatically scans the site when you open it without us clicking the button
- only alerts when there's misinformation
- pro plan?
- website bias checker
- there are some tools out there that can tell you how biased a website is / what their media bias is
- https://www.allsides.com/media-bias/media-bias-chart
- can try to find an api? if not, just hard code some shit
- cache results?
- edit dom
- when we find misinformation in the text, highlight it in red
License
MIT
Analysis
View
Metric
- 15
- 11
- 11
- 4
Figures cover GitHub contributors during the hackathon window. A co-authored commit counts in full for each author, so per-member totals add up to more than the whole-team figures.
Technology
- CSSIn code
- HTMLIn code
- JavaScriptIn code
3 of 3 appear in the indexed code.
AI coding agents
No AI coding agent signals were found in this repository.
Detected from committed agent config files and commit authorship. Absence of a signal is not proof an agent was unused.
Codebase size
Source size
46 KB
Source files
13
Counts recognized source files only; vendored directories, binaries and lockfiles are excluded, so this is smaller than the repository on disk.
Repository
tomayyeung/groq-is-this-true
19 files · 2.9 MB · @ 7550b32
Structure
Interface
4 files · 21%Screens, components and styles rendered to the user.
Application logic
9 files · 47%Domain rules, services and shared utilities.
Supporting
Layers are inferred from where files sit in the tree, not from reading the code. A project that names its directories unconventionally will read oddly here — open the file browser to check anything the diagram implies.
Languages
- JavaScript67%
- HTML15%
- Markdown13%
- CSS6%
Share of indexed source by file size. Binary and vendored files are excluded.
Dependencies
package.json
npm · 2- groq-sdk
- +1 more
Declared in the repository’s manifests at the indexed commit. A declared package is not proof it is used, and runtime dependencies are listed first.
This project’s features have not been analysed yet.
Export this project's context (description, README, evidence, key source files) to chat with an AI agent elsewhere.