A laptop and an iPhone on a desk, showing an illustrative personal workbench.

Your workbench.
Within reach.

Step away from your desk. Keep your Agent work moving with your voice.

Illustrative scene and interface

How can an iPhone connect to your own Agent workbench?

Yihu is a native iOS browser shell optimized for Agent workbenches: open your own HTTPS web UI, transcribe speech drafts on the phone, retain voice notes, filter PM Radar items and stage content through system sharing. Apple Watch can receive paired-phone summaries. Yihu supplies no Agent backend; speech needs separately downloaded models and native enhancements depend on service compatibility. Merged source does not certify every device path.

Your familiar workbench. A native touch.

On-device speech / Voice notes / Sharing

A thought.
Then a draft.

Try the handoff. Play a short sample, edit the words, then place them in a workbench draft.

INTERACTIVE DEMOSample content · no microphone access
  1. 01Listen
  2. 02Review
  3. 03Insert
A thought, out loud.
My workbenchDemo
Draft

Your reviewed words will appear here.

You decide what to send, and when.

Less distance between you and your work.

On-device speech

Say it while it’s fresh.

Turn spoken ideas into an editable draft on your iPhone. Review your words before sending. Speech models are downloaded separately.

Voice notes

Give a longer thought room.

Record now, transcribe in segments on your phone, and return to your audio and text later.

System sharing

Keep what you find.

Bring text, links and files into the share inbox. Choose what to hand off to your workbench. Nothing is sent automatically.

Your workbench.
Still yours.

Connect your own trusted HTTPS workbench. Yihu adds native iPhone capabilities around it.

Collie, OpenClaw and Hermes are examples of web workbenches you can open. Page access and native integration are separate capabilities.

Notifications and Live Activities require a compatible service. Yihu does not host Agents or provide a backend.

See what you need

Capabilities and prerequisites

Swipe the table to compare prerequisites. With a keyboard, focus the table and use the arrow keys.

CapabilityWhat it doesPrerequisites and boundaries
On-device speech draftsTranscribe on the phone and explicitly insert into a compatible draft; never presses Send.Download compatible models and grant microphone access; host refusal or unknown editors can prevent insertion.
Segmented voice notesRetain local audio and transcripts for later review.Requires compatible models and microphone access; remaining recording paths need device acceptance, with no accuracy guarantee.
PM Radar task filtersFilter tasks per workbench and distinguish source-read time from offline cache.Supply a JSON export or compatible HTTPS JSON feed; web cookies are not reused. Replies need separate authorization, phone confirmation and receipt readback.
Apple Watch summariesReceive pending decision/acceptance summaries from the paired phone and hand off to it.Requires watchOS 11+ and a paired phone; no standalone approval or direct Watch writes. Remaining device checks are pending.
System share inboxStage text, links and files before a user-selected handoff.No automatic upload or send; the destination service's data practices still apply.

Frequently asked questions

How can I access my own Agent web workbench on an iPhone?

Yihu is a native iOS browser shell around WebKit for your own reachable, trusted HTTPS workbench. Collie, OpenClaw and Hermes are web-access examples, not a certified native compatibility list. Yihu does not host Agents and is not their official client.

What do I need before connecting a phone to a self-hosted Agent workbench?

You need iOS 18+, your own trusted HTTPS workbench and, for the current source release, a Mac, Xcode, XcodeGen and your own signing setup. Speech also requires separately downloaded compatible models and microphone permission. Login and page compatibility depend on the server.

How can an iPhone turn speech into an Agent workbench draft without sending it?

Yihu transcribes on the phone with separately downloaded Qwen3 ASR models. After review, text can be inserted into a compatible draft. Insertion respects explicit host refusal, does not force text into unknown editors and never presses Send. Incompatible pages retain text for explicit copying.

Can an iPhone transcribe longer recordings in segments and keep local notes?

Yihu source includes longer recordings, segmented phone transcription and local audio/text retention, requiring microphone permission and compatible models. Remaining recording-related device checks are pending; no arbitrary duration, device performance or transcription accuracy is guaranteed.

How can I filter pending decisions and acceptance items across Agent projects on a phone?

Yihu PM Radar accepts your own JSON export or compatible HTTPS JSON feed, with per-workbench filters, management counts and bounded offline snapshots. Source-read times distinguish cached from fresh data; reads do not change ledger status. Authenticated feeds currently require a file export; Radar does not reuse web cookies or store credentials.

Does replying to a project decision from a phone automatically change task status?

No. For eligible decision/acceptance items, Yihu requires separately authorized server writes and explicit phone confirmation, followed by receipt readback. It does not automatically change status, execute tasks, merge or deploy. Real replies still require separate device/service acceptance.

Can an Apple Watch show Agent project summaries and approve them independently?

The watchOS 11+ companion receives pending decision/acceptance summaries through the paired phone and can hand off selected items or protected drafts to it. It does not provide standalone approval or direct Watch writes; the phone still requires confirmation and remaining pairing/device checks are pending.

Does sharing to a workbench on iOS automatically upload files or send messages?

Yihu's share extension stages text, links and files in an App Group inbox. It does not automatically upload or send them. Handoff requires a separate user action, and the destination workbench's data practices still apply.

Does on-device speech recognition mean all workbench app data stays on the phone?

No. Compatible downloaded models transcribe on the phone and voice notes are stored locally, but model downloads, web access, user sends/uploads and optional notification/relay integrations involve their respective services. On-device transcription is not a promise that all data stays on the phone.

Does opening an Agent web page mean native push and Live Activities will work?

No. Native notifications need a compatible web bridge, server endpoints and APNs configuration matching the signing environment. Live Activities also need a compatible relay you control. The placeholder relay is unusable, delivery needs separate acceptance and a ledger GET feed is not itself a push event source.

How can I currently install this type of self-hosted workbench iPhone client?

Yihu currently provides source code, not an App Store binary. Follow the repository build guide to configure your own identifiers, App Group and signing, then build for your iPhone. No preconfigured server or model files are supplied.

Can phone speaker verification replace account authentication or write authorization?

No. Yihu speaker verification is a convenience filter that can misidentify speakers, not authentication. Compatible WeSpeaker/CAM++ artifacts are not included; verification-dependent paths are unavailable without them. Verification and server write authorization must not be bypassed.

Take your workbench with you.

Open source. Built for iPhone. Connect your own services.

Get started

Currently a source release. Requires iOS 18+, your own workbench, speech models and signing setup.