TokKong Local AI

TokKong Local AI — Process web content with your own language model, offline and private. FEATURES - Extract & summarize web page text, articles, and transcripts - Query page content using retrieval-augmented generation (RAG) - Chat with documents using local LLM inference - All processing runs locally — your data never leaves your device HOW IT WORKS This extension connects to a local API service (TokKong, running on your machine) and sends selected text for processing. The local LLM analyzes, summarizes, or answers questions about that content, then returns results directly to your browser. PRIVACY & DATA - No data sent to external servers or cloud services - Processing requires a local TokKong instance running on http://127.0.0.1:47821 - Page content is only sent to your local API service - Results are cached locally in your browser REQUIREMENTS - TokKong local API service must be running - Supported models: Llama 2, Gemma, Qwen, and compatible GGUF formats PERMISSIONS EXPLANATION This extension requests broad host permissions to extract text from any webpage you're viewing. Data is only sent to your local API service; no external network requests are made.