HermannBjorgvin/Clawdmeter

ESP32 desk dashboard that shows Claude Code usage

What it solves

Clawdmeter is a physical desk dashboard for monitoring Claude Code usage and rate limits. It provides a real-time visual indicator of session and weekly utilization, reducing the need to check usage stats manually within the software.

How it works

  • Data Retrieval: A background daemon (Python) runs on the host machine (macOS, Linux, or Windows), reads the user's Claude OAuth token, and polls the Anthropic API for usage headers.
  • Communication: The daemon pushes usage data to an ESP32-based device over Bluetooth Low Energy (BLE).
  • Display: The firmware (C++/LVGL) parses the JSON payload and updates an AMOLED screen with usage percentages and reset timers.
  • Visuals: The device features pixel-art animations of the mascot "Clawd" that change based on the usage rate.
  • Control: The device acts as a BLE HID keyboard, allowing users to send shortcuts (Space for voice-mode and Shift+Tab for mode-toggle) directly to the host machine.

Who it’s for

Developers and power users of Claude Code who want a dedicated hardware monitor for their AI usage limits and a physical shortcut controller.

Highlights

  • Multi-platform Support: Dedicated installers for macOS, Linux, and Windows.
  • Hardware Flexibility: Supports multiple Waveshare ESP32-S3/C6 AMOLED boards out of the box.
  • Interactive Animations: Usage-rate-dependent animations and attention alerts that notify the user when Claude Code is waiting for input.
  • HID Integration: Physical buttons for push-to-talk and mode switching.
  • Customizable: Includes a desktop simulator for UI iteration and tools for converting assets into C arrays.

Related

  • Project
    GPT-AGI/Clawd-Code

    Clawd‑Code is a Python re‑implementation of Anthropic’s Claude Code agent, providing a streaming REPL, tool‑calling loop, multi‑LLM provider support, and extensible markdown‑based “skills”. It ships with a full CLI, 30+ built‑in tools, tests, and documentation, and is installable via a simple virtual‑env setup.

  • Project
    xianyu110/clawbot

    Clawdbot is an open‑source, locally‑run AI assistant that connects to Claude, GPT, Gemini and other LLMs via configurable API‑proxy endpoints. It offers web and terminal UIs, Telegram/Discord/WhatsApp bots, and stores all data on the host. The README covers installation (Node 22+, npm or script), an onboarding wizard for model and channel setup, detailed JSON configuration for multi‑model proxies, common pitfalls (Node version, env‑var misuse, missing fields), and a full set of CLI commands for managing the gateway, logs, and diagnostics.

  • Project
    wesammustafa/Claude-Code-Everything-You-Need-to-Know

    A practical, up‑to‑date guide for Anthropic’s Claude Code CLI, covering installation, prompt engineering, custom slash‑commands (Skills), automatic Hooks, sub‑agents, JavaScript workflows, and the Model‑Context‑Protocol for external tool integration. Includes ready‑to‑copy `.claude/` examples for teams building AI‑augmented development pipelines.

  • Project
    0Chencc/clawgod

    ClawGod is a runtime patcher that modifies the official Claude Code binary to unlock hidden commands, remove safety/usage restrictions, add multi‑agent features, and fix reliability issues. It works by extracting Claude’s embedded JavaScript, applying regex patches, and running the patched code under a regular Bun runtime, auto‑re‑patching on updates.

  • Project
    lifemate-ai/embodied-claude

    Embodied Claude is a modular runtime that adds persistent memory, a simple need‑driven desire system, social context handling, and a first‑person field to an Anthropic Claude‑Code project, turning it into a situated AI companion. It works on Linux, macOS, WSL2, and Windows, starts with a hardware‑free “Core” profile, and lets you optionally attach cameras, microphones, speech synthesis, temperature sensors, or X‑social‑media integration via guided setup scripts.