OLLAMA_ORIGINS=* before launch to allow cross-origin requests./api/tags first — if found, uses Ollama native; otherwise falls back to OpenAI compatible.
thinkingBudget:0 is requested to save tokens; DeepSeek-R1's <think> blocks are still stripped so they don't leak.
Chatbox Lite — a single-file browser-based multi-model chat page.
Supports: OpenAI compatible / Claude / Gemini / Ollama / LM Studio · streaming · Markdown · code highlighting · KaTeX math · image vision · file upload (PDF/DOCX/TXT/code) · multi-session local persistence · light/dark theme · export/import.
Usage: open chatbox-lite.html in your browser, go to "Settings" and configure your API keys. All data is stored in localStorage and never uploaded.
CORS tip: browser-direct API calls are subject to same-origin policy. Official OpenAI/Claude/Gemini endpoints support CORS; if using a proxy, make sure CORS is enabled. For Ollama, set OLLAMA_ORIGINS=* before launch.
Shortcuts: Enter to send / Shift+Enter for newline / Ctrl+N for new chat.
Project: github.com/lfbear/chatbox-lite
Author: lfbear (小飞熊)
P.S. Not a single line of this codebase was typed by the author — Claude wrote it all. I'm just the guy standing next to it, pointing fingers and waving hands. 🫠