Unclaimed profileBuilt from public GitHub and Hugging Face activity. Trevin has not joined Lounge yet.Claim it
Not on Lounge yet
Trevin
developerTerry Davis never made it to the age of AI, so im here for him
Public projects
aphotic-hypr
Four identities. One desktop. Modular Plugins · Live Hot-Swapping · Seamless Customization · Resource-Aware (personal project)
QMLaiarchlinuxdev
speculum
monitor for a local LLM runtime (llama-swap, NInfer, Strata, more) -- metrics ported to berth.
Pythonlightweightllama-cppllama-swap
llm-tune
Agent skill: evidence-based local LLM tuning - quant, context, KV, sampling, harness settings, measured on one 24 GB RTX 4090
Python
oh-my-epiq
Oh-My-Epiq (OME): the Epiq you love with batteries included. Pocket edition. Local-first, git-backed issue tracker with a terminal, browser board, and agent MCP
TypeScript
berth
The VRAM leasing service for every GPU you run. Engines lease the card instead of grabbing it: llama.cpp, llama-swap, Ollama, vLLM, SGLang, ComfyUI and more on one GPU, no collisions.
Gocomfyuigolanggpu
Strix-Recon
Strix Recon Agent / Ollama LLM / Reconnaissance Agent / LLM Focused
Python
Likely stack
LlamavLLMOllamaMCP
