# AI use cases for Groki Bot (JosssphZhou/groki-bot)

Repo: [JosssphZhou/groki-bot](https://github.com/JosssphZhou/groki-bot) | Use cases: 3 | Page: https://dedupedai.com/use-cases/josssphzhou-groki-bot/

Groki Bot is an open-source desktop robot kit (M5Stack CoreS3 with a Stack-chan base) that includes firmware, a computer-side voice and MCP gateway, and a link to Grok Bot agents.

This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL.

- Talk to a Grok Bot agent through your robot: https://dedupedai.com/use-cases/josssphzhou-groki-bot/talk-to-grok-bot-agent-with-robot/
- Make the robot track your face as you move: https://dedupedai.com/use-cases/josssphzhou-groki-bot/make-robot-follow-your-face/
- Build and update the robot firmware from source: https://dedupedai.com/use-cases/josssphzhou-groki-bot/build-robot-firmware-from-source/

## How to talk to a Grok Bot agent through your robot with Groki Bot

Repo: [JosssphZhou/groki-bot](https://github.com/JosssphZhou/groki-bot) | Difficulty: Intermediate | Time: 1 hour | Basis: From the README

Flash the robot, run the Mac gateway, and say "Hi Grok" to talk with a Grok Bot agent.

**Who it is for:** A maker with a CoreS3 Stack-chan robot and a Mac who wants to speak with a Grok Bot agent hands-free at the desk.

**The problem:** Setting up a desktop robot to reach a Grok Bot agent by voice usually means wiring firmware, a computer service, and an agent link together by hand.

**The outcome:** The robot wakes on "Hi Grok" and holds a voice conversation with your named Grok Bot agent, using the Grok Bot app login on your Mac.

### Steps

1. Open the web flasher in desktop Chrome or Edge to write the firmware, then configure Wi-Fi on the setup page.
2. Clone this repository and run `cd gateway && uv sync --all-extras` to install the gateway dependencies.
3. In `gateway/.env`, set `STACKCHAN_VOICE_BACKEND=gbot` and your agent name and ID, because Gemini is the default backend.
4. Keep the Grok Bot desktop app signed in, run the login helper in a second terminal, and start the gateway as described in the quick start.
5. Point the robot at the gateway on the BLE settings page, then say "Hi Grok" to begin talking.

### Prompt to paste into your agent

```text
In the groki-bot repo, follow docs/quick-start.md to set STACKCHAN_VOICE_BACKEND=gbot and the agent name and ID in gateway/.env for <agent-name>. Report the gateway startup output and confirm that the robot responds to "Hi Grok".
```

### Caveat

Native voice is listed for macOS only, so a Windows or Linux computer will not run this path as described.

Risk, credentials: Native voice reuses the Grok Bot app login on your Mac through a login bridge, so keep that session private and do not share the gateway machine.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/josssphzhou-groki-bot/talk-to-grok-bot-agent-with-robot/

## How to make the robot track your face as you move with Groki Bot

Repo: [JosssphZhou/groki-bot](https://github.com/JosssphZhou/groki-bot) | Difficulty: Intermediate | Time: 1 hour | Basis: From the README

Use your Mac camera so the robot's servos keep you in view while you move around.

**Who it is for:** A desk hobbyist with a Stack-chan robot who wants the robot to face them during video calls or while they work.

**The problem:** A fixed desk robot looks away as soon as you lean or move, so it feels disconnected from the person it is meant to engage.

**The outcome:** The robot keeps facing you using face detection from your Mac camera and dual-axis servo steering, with expressive eyes shown on its screen.

### Steps

1. Flash the firmware with the web flasher in desktop Chrome or Edge and connect the robot to Wi-Fi.
2. Clone this repository and run `cd gateway && uv sync --all-extras` on your Mac.
3. Start the gateway as described in docs/quick-start.md and point the robot at it on the BLE settings page.
4. Sit in front of the Mac camera and move slowly from side to side to check that the robot follows your face.

### Prompt to paste into your agent

```text
In the groki-bot repo, read gateway/README.md and set up dynamic face tracking with the Mac camera for <robot-name>. Report whether the servos move when a face moves in front of the camera.
```

### Caveat

The README says face tracking uses your Mac camera, so the camera stays on while the gateway runs and the README does not describe any privacy controls.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/josssphzhou-groki-bot/make-robot-follow-your-face/

## How to build and update the robot firmware from source with Groki Bot

Repo: [JosssphZhou/groki-bot](https://github.com/JosssphZhou/groki-bot) | Difficulty: Advanced | Time: 2 hours | Basis: From the README

Compile the CoreS3 firmware yourself and push updates over Wi-Fi with on-device OTA.

**Who it is for:** A firmware developer or maker who wants to change the robot's behavior, not only use the default build.

**The problem:** Using the prebuilt firmware limits what you can change, and reflashing by cable every time slows down testing.

**The outcome:** You have a firmware build from this repository, flashed once and then updated over Wi-Fi through on-device OTA.

### Steps

1. Clone the repository with `git clone https://github.com/JosssphZhou/groki-bot.git` and open it. (inferred, check the README)
2. Read docs/build.md for the toolchain and build steps, then build the firmware from source.
3. Flash the first build with the web flasher in desktop Chrome or Edge, or as described in docs/build.md.
4. Connect the robot to Wi-Fi and use the on-device OTA update to deploy each later build.
5. Run the robot through one expression cycle to confirm the new firmware works.

### Prompt to paste into your agent

```text
In the groki-bot repo, follow docs/build.md to build the CoreS3 firmware from source and list the output artifacts. Verify that the build finishes without errors before any flash step.
```

### Caveat

The README points to docs/build.md for the source build, so the exact toolchain requirements live in that file and were not summarized here.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/josssphzhou-groki-bot/build-robot-firmware-from-source/
