Agent surface
Chat UI, Live / LiveLand, local settings, Skill registry, permissions, and task state stay on the phone.
How it works
The phone discovers your Mac. You approve. Then models appear on iPhone.
Gateway advertises a local service over Bonjour. PhoneClaw discovers it on the same network, asks you to pair, then adds Mac-side models to the iPhone model picker under remote models.
Architecture
Only inference moves to the Mac.
The iPhone remains the agent surface and permission boundary. The Mac contributes heavier inference as an optional local edge node.
Local pairing
Bonjour discovery and explicit approval connect only devices on your local network.
Inference source
Gateway uses Ollama, Codex CLI, Antigravity CLI, or other supported Mac-side providers.
Direct LAN path
The request goes directly to your paired Mac on the local network.
Setup
Four steps from Mac to iPhone.
The setup is intentionally explicit. Remote models are never used until you pair a Mac and select one.
1
Open Gateway on the Mac
Download PhoneClawGateway.app, open it, and allow Local Network permission. If macOS blocks first launch, right-click and choose Open.
2
Choose a Mac-side model source
For Ollama, install Ollama and pull a model. Gateway can also expose CLI-backed providers such as Codex CLI or Antigravity CLI.
3
Pair from iPhone
Open PhoneClaw on the iPhone, go to Mac Remote, select your Mac, then approve the pairing on the Mac.
4
Select a remote model
Mac-side models appear in the iPhone model picker. Return to chat and use PhoneClaw normally.
Data path
Ollama stays on the Mac. CLI providers follow their own policy.
With Ollama, inference stays on your Mac. With Codex CLI, Antigravity CLI, or another upstream provider, data handling is governed by that provider from the Mac onward. PhoneClaw Gateway uses the local LAN path between iPhone and Mac.
中文
Mac 只负责更重的推理，手机仍是 Agent 本体。
PhoneClaw Gateway 让同一局域网内的 Mac 成为可选远程推理源。iPhone 仍然保留聊天界面、Skill 路由、权限边界和任务状态。请求通过本地局域网发送到配对 Mac；选 Ollama 留在你的 Mac，选 CLI 或其它上游 provider 则以对应策略为准。