Hugpy Media
Three chat models, live images, and the Hugpy console
Self-hosted, GPU-pooling LLM inference run your own model fleet on your own hardware. One streaming, OpenAI-compatible API over transformers & llama.cpp. Inference you own.
Self-hosted, GPU-pooling LLM inference — pool a workstation GPU, an idle laptop, even a phone, behind one streaming, OpenAI-compatible API.
A model registry with on-demand load/unload, streaming chat, Whisper transcription, embeddings & summarization — 40+ models from a single console, on hardware you own.
Three chat models, live images, and the Hugpy console
Three chat models, live images, and the Hugpy console
Three chat models, live images, and the Hugpy console
Embeddable web console — mountConsole() + a PTY broker
The fleet's agent CLI — enroll any box into your central