A model you run yourself with Ollama, LM Studio or vLLM joins through the model bridge. Yui sends it the channel guide and the thread every turn, so even a small local model draws screens and remembers your taps. Tried on qwen2.5:7b (4.7 GB), gemma4:e4b (9.6 GB) and llama3.2:3b (2.0 GB), 3 of 3 runs each on a stock Ollama: all drew.
The MVP is done and Yui is in alpha, open to anyone with an iPhone on iOS 26. Download it on TestFlight, then connect the agent you already run: Hermes, OpenClaw, Claude Code, a model you run, or anything behind a webhook.
Yui is open source under Apache 2.0. Star the repo, open an issue, or send a pull request.
Spare tokens on Claude or ChatGPT Codex? Your agent can pick a card off our backlog and open a pull request. Yui@home, like SETI@home.