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 26 surfaces — and lets you steer them without leaving the keyboard.
Explore AgentDeck
Four focused views: what runs where, how it looks, how it works, and whether the tests pass.
Devices
Browse supported displays and controllers, then open the detailed compatibility matrix.
Design system
Rendered specs, source Markdown, metadata, tokens, assets, validation, and agent handover.
Live Preview
Change the agent and state to compare real renderer output across device classes.
Test Report
The latest CI run — passing tests, scenario coverage, trends, and known gaps.
Source Code
MIT-licensed monorepo on GitHub — bridge, plugins, firmware, apps.
26 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.
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:
- Anthropic API — content goes to Anthropic, which may process and retain it under the user's own Anthropic agreement and privacy terms.
- OpenAI-compatible server — content goes to whatever OpenAI-compatible endpoint the user enters. If that endpoint is a server on their own machine (Ollama, LM Studio, vLLM, llama.cpp), nothing leaves the device. If it is a remote third-party service such as OpenRouter, used with the user's own key, the turn content is transmitted to that third party and is handled under that party's terms.
- MLX local server — a server the user started on their own machine; nothing leaves the device.
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