Native iOS Skills
Calendar, Reminders, Contacts, Clipboard, HealthKit, translation, images, and explicit Web Search.
Mobile-native local AI agent framework
An iPhone Agent built for real mobile constraints: on-device models, native iOS Skills, scoped permissions, Live interaction, and optional Mac inference when the phone should stay light.
This is PhoneClaw for iPhone, the iOS on-device agent project.
Product
PhoneClaw treats the iPhone as the runtime for local inference, native Skills, permission checks, model downloads, memory budgeting, and Live interaction modes.
Gemma 4 E2B / E4B via LiteRT and MiniCPM-V 4.6 run on-device for private everyday tasks.
Calendar, Reminders, Contacts, Clipboard, HealthKit, translation, images, and explicit Web Search.
Voice, camera-aware LIVE mode, and Dynamic Island status for mobile tasks in motion.
Memory budgeting, model switching, resumable downloads, cache cleanup, and history trimming.
Pair a Mac over LAN to use Ollama or CLI models while the iPhone keeps the agent experience.
Framework
Desktop agent frameworks assume long-running processes, generous memory, broad file access, and easy background execution. PhoneClaw starts from the opposite constraints.
Text, voice, images, LIVE camera, widgets, Shortcuts, Control Center, and LiveLand entry points.
File-driven Skills, scoped tool lists, argument extraction, clarification, and safer multi-turn task handling.
Calendar, Reminders, Contacts, Clipboard, HealthKit, Web Search, and device-local summaries behind permission gates.
LiteRT local models by default, with optional Mac Gateway for heavier models on a trusted local machine.
Boundaries
PhoneClaw keeps chat, images, and personal data on iPhone by default. Explicit user actions add network paths: Web Search, opening a URL, or Mac remote inference.
Default inference, native Skill calls, Calendar, Reminders, Contacts, Clipboard, HealthKit summaries, images, and chat.
Realtime Web Search and opening a public URL send the request to the search provider or target website.
When paired, the request goes to your Mac on the LAN. Ollama stays there; CLI providers follow their own policies.
Mac Gateway
PhoneClaw Gateway turns a Mac on the same Wi-Fi into an optional local inference source. The iPhone still owns the chat UI, Skills, permission model, and task flow.
Deep dives
These pages are written for developers, search, and answer engines that need specific evidence instead of a product tagline.
Why PhoneClaw is designed from iOS permissions, memory, mobile entry points, and edge inference rather than copied from desktop Agent stacks.
LiteRT-LM, MiniCPM-V 4.6, mobile memory limits, and how model choice shapes local agent workflows.
File-driven Skills, tool allowlists, permission boundaries, and local tool calling on iPhone.
Dynamic Island, widgets, voice, camera, and mobile task status for an iPhone-native agent.
Direct answer-engine facts for entity identity, privacy, mobile agent architecture, models, Skills, and Mac Gateway.
Languages
PhoneClaw already has zh/en/ja product localization. The website now exposes canonical Chinese and Japanese landing pages with hreflang, so search engines can match language intent directly.