#Siti AI — visionOS app

A native SwiftUI chat app for visionOS, built on Ed Swift, the agent SDK over the same on-device Onde inference engine that powers the Tauri app at the repo root (through ed-agent). This is a separate native client, not a Tauri build target; Tauri does not support visionOS.

Project layout and build-target conventions (window sizing, xros/xrsimulator platform settings, App Group entitlements, solid-image-stack app icon) follow the SplitFireAIVision target in the sibling splitfire repo (../splitfire/frontend/xcode/splitfire/SplitFireAI.xcodeproj). The chat engine wiring (streaming bridge, model lifecycle, conversation persistence) uses Ed's stream, load(gguf:) and restoreHistory.

#Setup

Install XcodeGen if you don't have it:

brew install xcodegen

Generate the Xcode project and open it:

cd xcode
xcodegen generate
open SitiVision.xcodeproj

Set your development team under Signing & Capabilities (defaults to 2TQF86ZACD, the same team as the Tauri app's iOS build — see ../src-tauri/tauri.conf.json), pick a Vision Pro simulator or device, hit Run.

#Developing against a local Ed Swift checkout

project.yml pulls Ed from the published ed-swift releases (from: 1.1.0), the same way src-tauri/Cargo.toml pins ed-agent from crates.io. To try an unreleased change, point the package at a sibling onde-ed-swift checkout instead:

packages:
  Ed:
    path: ../../onde-ed-swift

Then build the visionOS slice in that checkout with make visionos. It needs the sibling onde-ed Rust workspace (ED_REPO defaults to ../onde-ed) and a nightly Rust toolchain with -Z build-std, since visionOS is a tier-3 target.

#What it does

On first launch, it downloads and loads the platform-default model (Qwen 2.5 3B on visionOS, same tier as macOS) and streams replies token-by-token. Conversations persist locally between launches. The model cache lives in the shared group.com.ondeinference.apps App Group, so a model already downloaded by the Tauri macOS/iOS build of Siti is reused here instead of being fetched twice.

Current MVP feature set:

• token-by-token streaming with a stop button
• local conversation persistence between launches
• model settings sheet for system prompt + sampling preset
• toolbar actions to reload the model or clear the conversation
• prompt suggestions when the conversation is empty

Not yet done: a real visionOS-native layout (ornaments, volumes, spatial windows) — this MVP is a single glass WindowGroup, functionally equivalent to the iOS/macOS chat view. Immersive-space exploration is a good next step once the 2D chat flow is verified end-to-end.

#Files