Stack Chan

Communauté IA et agents

M5Stack-based robot with an MCP server for AI-controlled interactions and emotions.

Installation

Les étapes d'installation sont dans la documentation ci-dessous. Documentation

Documentation

Tirée du README du projet sur GitHub, actualisée chaque semaine. Les liens ouvrent GitHub.

Sommaire
  1. Stack-chan
  2. Getting started
  3. Browser tools
  4. Supported hardware
  5. Repository contents
  6. Development
  7. Contributing
  8. License
  9. BibTeX

Stack-chan

日本語

Stack-chan is an open-source, JavaScript-driven, super-kawaii robot built with M5Stack.

This repository provides firmware with M5StackChan CoreS3 as its standard configuration, user applications called MODs, browser development tools, cases, and schematics.

Getting started

If this is your first Stack-chan, start with a preassembled M5StackChan and the browser tools.

1. Get an M5StackChan

The standard M5StackChan AI Desktop Robot (K151) package is enough to get started. The joystick remote controller is optional.

2. Flash the firmware

Connect M5StackChan to a computer with a data-capable USB cable, then open the Web firmware installer in Chrome or Edge. Select "M5StackChan CoreS3" as the device. You do not need to install the Moddable SDK or ESP-IDF.

[!IMPORTANT] Flashing this repository's firmware replaces the factory firmware supplied by M5Stack. To restore it, follow the restore procedure in the M5Stack product documentation and use M5Burner.

3. Try a MOD

Find published MODs and mini apps in the MOD Gallery. Choose a MOD, then run it in the simulator or install it on a device. Block-based samples can be opened directly in the block editor and changed.

Browser tools

Use the Stack-chan browser tools to set up a device, change its preferences, and create MODs in a browser.

ToolPurpose
Firmware installerFlash firmware to a supported M5Stack over USB
PreferencesChange Wi-Fi and device preferences over BLE
MOD GalleryFind, try, and install published MODs
Block editorCreate MODs with Blockly and run them in the simulator or on a device
Shape face editorArrange eyes and a mouth to create a custom Face
SimulatorRun MODs with the WebAssembly firmware and a 3D model
MediaPipe BLE trackingSend tracked face and hand movement over BLE

Supported hardware

The distributed firmware supports M5Stack, M5Stack Core2, M5Stack CoreS3, and M5StackChan CoreS3. M5StackChan CoreS3 is the standard configuration and the target used for physical-device release validation.

Firmware for Stack-chan RT and Takao Core2 + SG90 can be built from source. See the firmware guide for target-specific commands and constraints.

To build the hardware yourself, see the case guide for parts and assembly instructions. See the schematics for board information.

Repository contents

  • firmware: Host firmware, modules, MODs, and development scripts
  • web: Firmware installer, preferences, editors, Gallery, and simulator
  • case: Case models for 3D printing
  • schematics: Schematics and board layouts
  • docs: Roadmap, specifications, operations guides, and release notes

Development

Contributing

Feature requests, bug reports, and pull requests are welcome. Read the contribution guide, or open an issue.

To support the project financially, visit the GitHub Sponsors page.

License

The resources in this repository are distributed under the Apache License 2.0. See LICENSE.

BibTeX

@misc{stackchan,
  author       = {Shinya Ishikawa and the Stack-chan community},
  title        = {Stack-chan: A JavaScript-driven Super-kawaii Robot},
  year         = {2021},
  howpublished = {\url{https://github.com/stack-chan/stack-chan}},
  note         = {Open-source hardware and software.},
}

Questions fréquentes

Qu'est-ce que Stack Chan ?

M5Stack-based robot with an MCP server for AI-controlled interactions and emotions.

Comment installer Stack Chan ?

Suivez les étapes d'installation de sa documentation, affichée sur cette page et dans son dépôt.

Stack Chan est-il open source ?

Oui. Son code est sur GitHub sous licence Apache-2.0.

Qui maintient Stack Chan ?

Il est publié par stack-chan. AI.tn le référence sans le maintenir ni le recommander.

Issu des listes communautaires awesome-mcp-servers et du dépôt GitHub du projet. Être listé n'est pas une recommandation : vérifiez le code et les permissions d'un serveur avant de lui donner accès à vos données.