<2-3 sentences summarising what the project addresses and solves, the target audience, and the benefit.> This project delivers native iOS and Android clients for Codex, enabling direct mobile interaction with the Codex AI model. It supports both on-device Rust bridge integration for offline use and a remote-only mode, targeting developers and power users seeking mobile Codex access.

How It Works

The architecture employs a shared Rust bridge (codex-bridge) for core RPC client functions, integrating upstream Codex as a submodule with platform-specific patches. Native iOS and Android applications utilize this bridge; iOS offers distinct LitterRemote and Litter (on-device) schemes. The Android client uses Compose UI, state management, and a WebSocket client, while network components handle service discovery across Bonjour, Tailscale, and LAN.

Quick Start & Requirements

• iOS: Requires Xcode, Rust (targets: aarch64-apple-ios, aarch64-apple-ios-sim, x86_64-ios), and xcodegen. Setup involves bootstrapping scripts, syncing Codex submodule, applying patches, building the Rust bridge, regenerating the Xcode project (xcodegen), and opening apps/ios/Litter.xcodeproj. Schemes: LitterRemote (default) and Litter (on-device).
• Android: Requires Java 17, Android SDK (API 35), and Gradle 8.x. Build commands include :app:assembleOnDeviceDebug and :app:assembleRemoteOnlyDebug. Running involves emulator setup, adb install, and launching the app. Android Rust JNI libraries build via ./tools/scripts/build-android-rust.sh.
• TestFlight: Requires asc CLI authentication with App Store Connect API keys and specific build scripts for uploading.

Highlighted Details

• Native iOS and Android clients for Codex.
• On-device Rust bridge for offline Codex interaction.
• Vendored Codex source with platform-specific patches.
• Automated TestFlight build and upload process.
• Cross-platform Rust bridge compilation for mobile targets.

Maintenance & Community

No specific details regarding maintainers, community channels (e.g., Discord, Slack), or project roadmap are provided in the README.

Licensing & Compatibility

The repository's license is not explicitly stated in the provided README text. This absence requires clarification for adoption decisions, particularly concerning commercial use or integration with proprietary software.

Limitations & Caveats

Project functionality is tied to Codex AI model capabilities. Setup demands a complex toolchain and specific environment configurations for both iOS and Android. The lack of explicit licensing information is a significant adoption blocker.