Token Monitor - An ESP32-S3 desktop display that tracks AI coding assistant usage (Crowdfunding) - CNX Software
Skip to content
Fractal Manifold has introduced the Token Monitor, a 4-inch ESP32-S3-based desktop display for monitoring real-time AI coding assistant usage.<br>The device features a 4-inch 480×480 IPS touchscreen with 5-point capacitive touch, Wi-Fi 4 and Bluetooth LE 5 wireless connectivity, USB-C power, optional 1-cell Li-ion battery support via an AXP2101 PMIC, and two side buttons for power and boot functions. It shows usage information including quota consumption, session limits, token counts, reset timers, and estimated token costs. A local broker service fetches the usage data and transfers it to the device over a secure connection, keeping credentials on the user’s machine.
Token Monitor specifications:
SoC – Espressif Systems ESP32-S3
CPU – Dual-core Tensilica LX7 up to 240 MHz with vector extension for AI/ML workloads
RAM – 512KB SRAM; 8MB PSRAM
Wireless – WiFi 4 and Bluetooth LE 5
Storage – 16MB flash
Display – 4-inch 480×480 capacitive touchscreen with ST7701 driver and GT911 touch controller
USB – USB Type-C port for power
Power supply
5V via USB Type-C port
Internal 1S Li-ion battery (covers >5 hours of session time)
AXP2101 PMIC
Dimensions – 86 x 86 mm footprint
Enclosure – 3D-printed matte ABS shell; includes a dedicated desktop base
The device connects to an Apache-2.0 licensed, local open-source broker (tokenmonitor-mcp) running on a Mac or Linux PC, which parses CLI logs and fetches usage quotas directly from provider APIs. The broker also requires a local runtime environment with Node.js (≥20), Python 3.11+ (via uv, pip, or venv), or Go (≥1.25). It listens for LAN-based polling on port 8765 using HMAC-signed, replay-protected requests, so no telemetry or raw code is transmitted externally. The platform supports Claude Code, Codex CLI, and Antigravity CLI out of the box.<br>Another software feature is integration with the Model Context Protocol (MCP). The local broker acts as an MCP server and exposes 17 hardware management tools to AI assistants like Claude Code and Codex. This allows you to provision the ESP32-S3 over mDNS or USB-CDC serial, show ESP-IDF diagnostic logs, update Wi-Fi credentials, and install Ed25519-signed OTA firmware updates directly from the AI CLI. More information about the broker is available on the project’s GitHub repository.
The Token Monitor displays real-time Claude Code usage, including quota consumption and reset timers (with light and dark themes)
The firmware is based on LVGL. It also supports light and dark themes synchronized with local sunrise and sunset using Open-Meteo. There is also a customizable panel that can display user-defined JSON data from the local broker as line graphs, pie charts, tables, and text to monitor additional metrics beyond AI usage.<br>The Token Monitor adds to a long list of ESP32-based smart displays for AI coding assistants monitoring and control, such as the Claude Desktop Buddy, Clawdmeter, CtrlVibe AI Console keypad with built-in display, ZecTrix Note 4 E-Ink display (when used with vibecoding-voice/vibecoding-plus firmware), among others.
Token Monitor’s rear view showing the 3D-printed enclosure, ventilation slots, and desktop stand.
The ESP32-S3-based desktop Token Monitor is now available on Kickstarter with a funding goal of €25,000. The Super Early Bird reward is priced at €99 (about $115) for a white Token Monitor device, while the standard Early Bird tier costs €120. At the time of writing, I can only see delivery currently available to the US, Canada, the EU, and the UK, and the first units are expected to ship in November 2026.
Debashis Das<br>Debashis Das is a technical content writer and embedded engineer with over five years of experience in the industry. With expertise in Embedded C, PCB Design, and SEO optimization, he effectively blends difficult technical topics with clear communication
Share this:
Support CNX Software! Donate via cryptocurrencies, become a Patron on Patreon, or purchase goods on Amazon or Aliexpress . We also use affiliate links in articles to earn commissions if you make a purchase after clicking on those links.
Subscribe
Login
Notify of
new follow-up comments<br>new replies to my comments
Connect with:
Label
{}<br>[+]
Name*
Email*
Website
I agree to the Privacy Policy
The comment form collects your name, email and content to allow us keep track of the comments placed on the website. Please read and accept our website Terms and Privacy Policy to post a comment.
Connect with:
Label
{}<br>[+]
Name*
Email*
Website
I agree to the Privacy Policy
The comment form collects your name, email and content to allow us keep track of the comments placed on the website. Please read and accept our website Terms and Privacy Policy to post a comment.
0 Comments
oldest
newest
Load More Comments
Search...