The flagship on-device chat: a 76-model multi-provider selector (transformers, WebLLM, wllama GGUF, LiteRT) with capability gating, vision attachments, DeepSeek-R1 reasoning display, semantic response caching, agent mode with tools, custom GGUF URLs, system prompt + parameter controls, and slash commands — everything runs in the browser.
pnpm dlx shadcn@latest add "https://localmode.ai/r/ui/blocks/chat.json"