Physical control surface for AI coding agents

Stop Chatting.
Start Steering.

AgentDeck puts your coding agents on the desk. One daemon hub renders every session live across 29 surfaces — and lets you steer them without leaving the keyboard.

One coding task, five sessions: watch agents join, edit, test, wait for permission, and finish as the timeline fills. Recorded in the native iPad app with fictional sample activity. Silent, 43 seconds, 2752 × 2000; expand to full screen for detail.

Get AgentDeck

Start on your computer

The AgentDeck hub runs on your computer. Everything else connects as an optional companion surface.

29
display surfaces
1
shared session model
Local
hub on your computer
AgentDeck on the desk, September 28, 2026 — iPad and Android dashboards, e-ink readers, Stream Deck controls, Ulanzi D200H, ESP32 panels, and LED displays
One daemon across the desk. Photographed September 28, 2026; open the photo for the full setup.

Your agents, in view

Choose a dashboard that fits your screen and the way you work. Existing appearance choices stay yours.

Native aquarium

Work, then watch

Live 3D creatures on Apple and Android LCD screens. Mobile viewing mode fades the panels and brings the habitat closer. E-ink keeps its own calm, static backdrop.

Collaboration

Follow the handoff

See the selected task, recent task history, and reported subagent activity. Busy scenes keep up to eight foreground residents while the roster retains every session.

Across your devices

Keep the essentials close

Claude, Codex, and z.ai/GLM usage where available, adapted to the display. Android GitHub APKs update wirelessly from Settings; store installs use their store.

Explore AgentDeck

Five focused views: what runs where, how to put firmware on it, how it looks, how it works, and whether the tests pass.

Surface catalog

Devices

Browse supported displays and controllers, then open the detailed compatibility matrix.

Browser flasher

Flash firmware

Install ESP32 firmware over USB straight from Chrome or Edge — no checkout, no PlatformIO.

Living system

Design system

Rendered specs, source Markdown, metadata, tokens, assets, validation, and agent handover.

Interactive renderer

Live Preview

Change the agent and state to compare real renderer output across device classes.

CI evidence

Test Report

The latest CI run — passing tests, scenario coverage, trends, and known gaps.

Open source

Source Code

MIT-licensed monorepo on GitHub — bridge, plugins, firmware, apps.

29 surfaces, one bridge

The same session state renders natively on each, and they run simultaneously — counted from the canonical compatibility matrix. Each app chip is a separately designed UI; the XTeink readers run the community CrossPoint fork.

Stream Deck+8 keys · 4 dials
Stream Deck15 keys
Stream Deck Mini6 keys
Stream Deck XL32 keys · 8×4
Stream Deck + XL36 keys · 6 dials
Ulanzi D200H960×540 · 14 keys
Ulanzi D200X960×540 · 14 keys · encoder support pending
macOSSwiftUI dashboard + hub
iOS / iPadOSSwiftUI companion
Android TabletCompose color dashboard
Android E-inkCompose reader layouts
ESP32 IPS 3.5"480×320
ESP32 86 Box 4"480×480
Round AMOLED 1.8"360×360
ESP32 IPS 10.1"800×1280
TTGO T-Display135×240
Waveshare LCD 1.47"172×320
T-Embed Companion Knob320×170 · encoder
T-Display-S3-Pro Focus Strip480×222 · touch
TRMNL 7.5" e-ink800×480 · WiFi OTA
RockBase NM-EPD-420400×300 · tri-color e-ink
LilyGo T5 ePaper S3960×540 · grayscale e-ink
XTeink X3528×792 e-ink · fork
XTeink X4480×800 e-ink · fork
Divoom Pixoo6464×64 LED
Ulanzi TC0018×32 LED
iDotMatrix32×32 LED
Timebox Mini11×11 LED
TUI Dashboardterminal

Privacy Policy

Effective date: July 15, 2026

AgentDeck Dashboard is a local monitoring and evaluation app for AI coding agent sessions. It does not require an account, does not show ads, does not sell personal data, and does not operate a remote analytics service.

Data Stored On Device

AgentDeck stores app settings, local pairing state, session timeline data, cached evaluation results, and optional hardware configuration in the app sandbox on the user's device.

Optional Integrations

Users may opt in to local integrations such as Claude Code hooks, Codex lifecycle hooks, OpenClaw Gateway pairing, Kiro CLI observation, iPhone/iPad dashboard pairing, voice input, ESP32, Pixoo, or D200H hardware support. User-selected hook configuration files are accessed only after explicit file picker consent, and Kiro observation reads the user's own ~/.kiro folder only after they grant access to it in Settings; without that grant AgentDeck observes nothing.

Optional Remote Model Services

Evaluation runs on the on-device Foundation Models backend by default, which contacts no network endpoint. The user may instead select an opt-in remote backend and supply the endpoint and their own credential. When they do, AgentDeck sends the agent turn content needed for evaluation, and the associated API interaction data, to the endpoint the user chose:

These backends are off by default, are used only for app functionality, are linked to the user through the credential they supplied, and are never used by AgentDeck for tracking, advertising, or marketing. AgentDeck operates no server of its own and receives none of this content.

Network, Voice, and Credentials

Local network connections are used for same-device hooks and paired iPhone/iPad dashboard display. Optional local services are contacted only when configured by the user. Voice input uses Apple's speech APIs for the requested command flow. Optional credentials, such as an Anthropic Admin API key, an OpenAI-compatible endpoint key, or an OpenClaw shared token, are stored in the macOS Keychain and used only for the configured feature.

Contact

Questions: admin@foundby.kr