Skip to content
RobothecaBeta
Log in

Coglet

A DIY desktop companion robot for makers, with a camera, microphone, speaker and nine servos for expressive movement.

  • Home
  • Works with AI
  • 3D printable

Suggested by Robotheca, created by @will-cogley (opens in a new tab), from github.com/will-cogley/Coglet (opens in a new tab). Pinned to commit 84b6612 (opens in a new tab).

Fork on GitHub (opens in a new tab)Download the files at this commit (.zip)
Hardware license
CC-BY-NC-4.0 (opens in a new tab)
Software license
CC-BY-NC-4.0 (opens in a new tab)
Commercial use
Not allowed

A non-commercial license (CC-BY-NC) does not allow selling kits or parts.

Some folders have their own license: CogletESP/ (MIT).

This repository contains executable files that Robotheca doesn't check. Only run them if you trust the creator.

Which files (1 script)

Photo and 3D model

Its license doesn't let Robotheca show its photos.
See the photos on GitHub (opens in a new tab)

3D model loaded from the original files on GitHub at 84b6612, under CC-BY-NC-4.0. View the original files from GitHub (74.4 MB) (opens in a new tab)

What it can do

Written by Robotheca from the project's documents.

  • Desktop companion robot built around the CogNog PCB, controlled through an ESP32 running XiaoZhi AI chatbot firmware.
  • Voice interaction using streaming speech recognition, a large language model and speech synthesis.
  • Device-side MCP control of speaker, LED, servo, and GPIO features.
  • Vision via a Grove Vision AI V2 camera and an ESP camera, with face tracking eyes.
  • Animated expression on OLED or LCD displays with emoji support.
  • Offline wake-word detection using ESP-SR.

Works with AI

Found by Robotheca in the project's files at commit 84b6612, its robot.yaml and Robotheca's notes on its documents. Never guessed; Robotheca doesn't run the code.

Bill of materials

This repository has no parts list Robotheca can read yet.

Build guide

The guide appears here as you scroll.

Guide by @will-cogley (README.md). Its license (CC-BY-NC-4.0) doesn't let everyone reuse it. To reuse it, ask the creator on GitHub (opens in a new tab). Creators can ask Robotheca to remove it at contact@robotheca.org.

More guides

Wiring and electronics

Notes written by Robotheca from the project's documents.

Main parts

  • CogNog PCB as the main board.
  • ESP32 microcontroller running the XiaoZhi firmware (ESP32-C3, ESP32-S3 or ESP32-P4 supported).
  • Grove Vision AI V2 camera module with adaptor and 15-pin flex cable.
  • Microphone (INMP441-type I2S microphone).
  • Speaker.
  • Nine 9g hobby servos, with TorqueStar spline adapters.
  • Realistic camera-compatible eye mechanisms.
  • USB power input (3A recommended) and a battery display/power management option.
  • RP2040 scripts are also present in the repository, suggesting a secondary microcontroller.

Connections

  • Components connect to the CogNog PCB, which the documents describe as the central connection point.
  • The microphone and speaker connect to the ESP32 audio pins according to the breadboard wiring diagrams.
  • A 6-pin PicoBlade connector links a module to the board.
  • The camera connects via a 15-pin flex cable to the Grove Vision AI module.
  • Wiring diagrams for breadboard builds are provided in the repository images and translated tutorials.