Infrastructure for the next generation of voice agents, designed to provide universal memory. It is divided into a left brain and a right brain, storing information and emotions respectively, while a fully streaming architecture eliminates latency at the fundamental level.
Repository Index
47,133 repositories indexed
1–4 of 4 · Most stars
Low-latency local speech-to-speech voice assistant with Ming-3.0-audio-tiny on AMD and Nvidia GPUs. Easy setup on Windows and Linux
- amd
- local-llm
- radeon
- realtime
Fortnite FPS Booster: frame-rate stability, lower input latency, process priority tuning, memory cleanup and power-plan presets for Fortnite on Windows. Lightweight, reversible, open-source performance optimizer.
Fast, exact inference for StartLux-Decision models on NVIDIA GPUs: the released GGUF files on int8 and 4-bit tensor cores, behind the /v1/systemone API, with up to 5.3× lower latency than vLLM in FP8 and bit-identical answers.
- calibration
- cuda
- cuda-graphs
- decision-making