Features of core.ml
Boost your AI workflow
Local model in the browser
Chat with a powerful AI model running entirely in your browser. No data is sent to external servers.
Upload your files and MCP
Leverages your GPU for accelerated AI inference through WebGPU technology, making interactions faster and more responsive.
Agents collaboration
Model responses support markdown formatting for rich text, code blocks, lists, and other structured content.
Reasoning and long context
Works across different platforms and devices as long as they have a compatible browser with WebGPU support.
Libraries and news RAG
Model is cached in your browser's storage after first load, enabling faster startup times on subsequent visits.
Voice to learn and interact
Watch as the model generates responses in real-time, providing a more interactive and engaging experience.