LocalMode
Run AI entirely in your browser, no servers or API keys
LocalMode is an open-source (MIT) toolkit for running AI entirely in the browser with no servers, no API keys, and data that never leaves the device. It supports LLM chat with over 76 models, plus RAG and vector search. It includes Whisper speech-to-text and Kokoro text-to-speech with 29 voices, as well as on-device vision features like image classification, object detection, and CLIP search. The toolkit has a zero-dependency core with 64 React hooks and a shadcn UI registry of 107 components and 36 installable blocks. It runs on WebGPU with a WebAssembly fallback and works offline after the initial model download.
More like LocalMode
Startups doing something similar, featured in the last two years
Get a daily risk score for your code, dependencies and licenses
Run powerful AI models locally on your Mac and iPhone
Run a real LLM in your browser with no install or server
Practice sales calls with AI buyers and get instant coaching
Run powerful local AI on your Mac with voice and tools, no setup
Local-first AI IDE with your own LLM and no subscription
Get daily AI insights on models, frameworks, and local LLMs
Build and run AI agents inside your browser, private and 0 cost
Instant AI assistant on your browser
Build AI apps locally on Mac with an agentic IDE and safe deploys
Control your AI app: protect, observe, and govern every LLM call