AiRC vs LLLM

AiRC is the native iPhone and iPad remote for AiRC Orchestration on your computer. Continue the same conversations from your phone or your Mac, follow streaming replies, and keep work running on your host. A compatible AiRC Orchestration host is required. Install the desktop app, enable companion access, and pair using its one-time QR code. Your device must be able to reach that host over your local network or a private network connection. AI-provider accounts, model availability, and any provider charges are managed on the host. YOUR CONVERSATIONS • Open recent messages quickly and load earlier history when you need it. • Organize chats by project, priority, pinned items, or time. • Start a chat without a project, or create one directly inside a project. • Choose an available provider, model, and reasoning effort supplied by your host. • Follow replies and tool progress live, review supported approval requests, and stop a run. YOUR HOST WORKSPACE • View goals, plans, orchestration, and individual agents. • See token speed, context use, and cost when your host and provider supply them. • Access host-backed Automations, Skills, Recipes, Apps, Extensions, Session History, Documentation, and Settings. • Compact a conversation from its context controls. • Follow supported Computer Use, in-app browser, and Playwright activity in a floating, expandable preview. FILES THAT FIT THE CONVERSATION • Add supported photos and documents to a message. • Open saved images and supported documents in a native preview. • Share or download files, with Save to Files and supported Photos destinations. • Keep routine code and tool output collapsed until you choose to expand it. Work executes on your paired computer. AiRC on iPhone and iPad does not run desktop tools or large language models locally. Available features depend on your host version, its configuration, and the selected provider. Locked-phone push notifications are not part of this release.

Chat app compatible with Ollama and self-hosted models. It needs an Ollama server running and adding the endpoint in the model settings. All the information saved is local, everything is private, and no account is needed. It supports message streaming and markdown. It could also work with models served without Ollama, but that has not been tested.