AOS: Agent Operating System
A research prototype for agent collaboration through runtime primitives: artifacts, messaging, capabilities, and scheduling.
AI, Graphics, and Doodling.
Peihong Guo is a Senior Staff Research Engineer at Meta Reality Labs, working on real-time graphics and visual computing. Those three words are also what this site keeps growing: models run and probed on machines you can point at, renderers written to find out how light actually reaches a pixel, and a crayon-doodle shelf of bedtime picture books drawn to a four-year-old's specifications.
Currently
AI — Qwen served from a machine under the desk, an Android voice assistant that runs it locally, generative AI, and agent prototypes built on the same idea. Graphics — a raytracer that finally takes refraction seriously, with real-time work at Reality Labs in between. Doodling — Wukong & Friends, a bedtime story garden with signed PDFs.
Selected work
Featured projects
Jarvis Voice Assistant
An Android voice assistant with local Qwen inference, speech models, home-control tools, and a background update pipeline.
Generative Facial Keypoints
Exploring image-conditioned diffusion and flow matching for facial landmarks with frozen DINO features and transformer coordinate models.
Wukong & Friends
Crayon-doodle bedtime picture books for young readers, with free reading and two-up booklet PDFs, published from a private repository against an Ed25519-signed manifest.
Recent writing
Blog highlights
Introducing Wukong & Friends
Free read-aloud picture books, built to make bedtime calmer for a four-year-old — and the unglamorous machinery behind them: keeping one character recognizable from book to book, signing every PDF, and publishing a private repository's build into a public subdirectory.
A Local-Only Garage Door Opener for Apple Home
Two ESP8266 boards, one Homebridge accessory plugin and no vendor cloud: how the pieces fit together, and how many of the design decisions were forced by an opener with a single momentary input.
Deploying Qwen on Intel Arc with vLLM and DFlash2
Serving a quantized Qwen model on a single 32 GB Intel GPU: cache budgets, speculative decoding, long-context performance, and deployment lessons.