A Chrome extension that lets you select any online claim and instantly receive a grounded credibility assessment.
The Reality Button analyzes text (headlines, social posts, claims) and returns:
- Verdict (true / false / misleading / mixed / unclear)
- Confidence score
- Concise explanation
- Supporting sources
Misinformation spreads faster than verification. Most people don’t fact-check because it’s too slow and inconvenient.
This project reduces that friction to one click.
Frontend
- Chrome extension with a popup UI and user-initiated right-click action
- Users can paste a claim or verify selected webpage text without broad page access
Backend
- Node.js server deployed on Google Cloud Run
AI + Retrieval
- Supports Gemini 3.6 Flash (recommended default), Gemini 3.5 Flash, and Gemini 3.5 Flash-Lite
- Enables live Google Search grounding for current information and supporting sources
- Parses output into structured format
Architecture Chrome Extension → Cloud Run API → Gemini (with search grounding) → Structured response
The system uses live search instead of relying on model memory, which is critical for:
- current events
- political claims
- fast-changing information
Users provide their own Gemini API key:
- avoids centralizing user credentials and usage costs
- lets users retain control of their own quota and billing settings
- mirrors real-world API-enabled products
Instead of forcing fragile JSON from the model:
- the system uses structured text
- parses deterministically on the backend
- improves reliability
Input "Vaccines cause autism"
Output
- Verdict: FALSE
- Confidence: 95%
- Explanation + sources (CDC, WHO)
cd Server
npm install
node server.jsGo to chrome://extensions Enable Developer Mode Click "Load unpacked" Select project folder
In the extension:
- Follow the guided setup to create and add a Gemini API key
- Review and accept the data-use disclosure
- Choose a supported Gemini model in Settings
Public-release candidate with guided onboarding, grounded verification, minimized Chrome permissions, and documented privacy practices.
Read the Privacy Policy for details about claim processing, API-key handling, retention, and user controls.
- Better confidence calibration
- Claim clustering and repeated-claim detection
- Caching to reduce API calls
- Source-to-claim citation mapping