Token Monitor: ESP32-S3 desktop display for tracking AI coding assistant usage

The Token Monitor addresses a specific niche in the growing ecosystem of AI coding assistant monitoring tools. By running a local broker service, the device shifts data processing away from cloud services, giving users direct control over where their usage information flows. This design choice aligns with privacy concerns common among developers who use AI assistants for production work. The integration with the Model Context Protocol is particularly significant because it allows AI assistants themselves to manage the device's configuration and updates—provisioning the ESP32-S3, retrieving diagnostics, and installing firmware—all without leaving the CLI. This closes a loop between monitoring and control that most existing tools do not offer.

The hardware specifications reflect a pragmatic balance between capability and cost. The ESP32-S3 dual-core processor, 512KB SRAM, and 8MB PSRAM are sufficient for running LVGL-based UI rendering and maintaining a local WebSocket connection; the optional 1-cell Li-ion battery (which supports over 5 hours of session time) allows desk placement away from a power outlet. The 4-inch 480×480 touchscreen is large enough to display meaningful data without consuming significant desk space. Fractal Manifold positions the Token Monitor within an existing category of ESP32-based AI assistant displays—including the Claude Desktop Buddy, Clawdmeter, CtrlVibe AI Console, and ZecTrix Note 4—each targeting similar developer workflows but with different feature sets and form factors.