Local LLM chat, speech and image generation running entirely in your browser on the GPU, with no server doing the inference - built on SpawnDev.ILGPU.ML, which transpiles C# to WebGPU compute shaders.
Sign in with Hugging Face and press 🤗 Connect my Reachy to give a character a body. The connection goes over WebRTC through the central signalling Space, so it reaches your own robot - the one registered to the account you signed in with.
Everyone else in the scene stays on screen.
Local LLM chat, speech and image generation running entirely in your browser on the GPU, with no server doing the inference - built on SpawnDev.ILGPU.ML, which transpiles C# to WebGPU compute shaders.
Sign in with Hugging Face and press 🤗 Connect my Reachy to give a character a body. The connection goes over WebRTC through the central signalling Space, so it reaches your own robot - the one registered to the account you signed in with.
Everyone else in the scene stays on screen.