Physical control surface for AI coding agents
AgentDeck turns Stream Deck+, e-ink readers, tablets, ESP32 displays, LED matrices, and terminals into a live cockpit for Claude Code, Codex, OpenCode, and OpenClaw — one daemon hub, up to 16 surfaces at once, steered without leaving your keyboard flow.
Everything about the project, organized for whatever brought you here.
Every dashboard surface — SoC, resolution, flash, transport, App Store tier.
The real hardware, board by board, with live specs.
Architecture, devices, evaluation, protocol, design system.
Per-device renderer output for every agent & state.
Coverage, scenario matrix, and history across all test suites.
MIT-licensed monorepo on GitHub — bridge, plugins, firmware, apps.
The same session state renders natively on each, and they run simultaneously.
Effective date: July 10, 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.
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.
Users may opt in to local integrations such as Claude Code hooks, Codex lifecycle hooks, OpenClaw Gateway pairing, 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.
If the user explicitly selects the Anthropic API evaluation backend and provides their own API key, AgentDeck sends the agent turn content needed for evaluation to Anthropic. Anthropic may process and retain that content and associated API interaction data under the user's Anthropic agreement and privacy terms. This integration is off by default, is used only for app functionality, is linked to the user's Anthropic account through their API credential, and is never used by AgentDeck for tracking, advertising, or marketing. Users can instead keep the on-device Foundation Models backend selected.
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 or OpenClaw shared token, are stored in the macOS Keychain and used only for the configured feature.
Questions: puritysb@gmail.com