A privacy-focused browser extension that runs Large Language Models locally via WebLLM without sending data to external servers. It leverages browser-based GPU acceleration to provide an offline-capable AI chat interface.
Tech Stack
TypeScriptAI, ML & Data
Why localGPT?
• Complete data sovereignty
• Works without internet connection
• Powered by WebLLM for performance
Limitations
• High local hardware requirements
• Limited by browser memory constraints
• Slower than cloud-based LLMs
8/21/2025
Last Update
3
Forks
1
Issues
Apache-2.0
License
Financial Leak Detected
Stop the "SaaS Tax"
Your team could be burning cash. Switching to localGPT instantly boosts your runway.
