PROJECTS
Projects
Things I built from scratch, and what I’m working on right now.
01In Progress
Self-hosted agent runtime on one machine
Conversation is only the entry point — the capability lives in the tool layer, the memory layer, and the scheduler. 94 tools are isolated per role, long-term memory both forgets and distills, and six clients share one backend.
Python / FastAPI / C++ / llama.cpp / React / Kotlin / Swift / Docker
LLM residency, image bursts, and CPU backfill on a single GPU
A research prototype: on one GPU an LLM stays resident, image generation arrives in bursts, and CPU work backfills the gaps. The work covers admission control, migration cost, and crash recovery; the experimental results go into a thesis.
Python / C++ / CUDA / PyTorch / FastAPI / WebSocket / llama.cpp