LocalMode is an open-source (MIT) toolkit for running AI entirely in the browser - no servers, no API keys, and data never leaves the device.
• LLM chat over 76 models, plus RAG and vector search
• Whisper speech-to-text and Kokoro text-to-speech (29 voices)
• On-device vision: image classification, object detection, and CLIP search
• A zero-dependency core with 64 React hooks
• A shadcn UI registry of 107 components and 36 installable blocks
• Runs on WebGPU with a WebAssembly fallback, and works offline after the first model download
