Welcome to RDK X5 Board repository
1. Plant Care Assistant
OpenClaw Plant Care Butler Tutorial
Before starting, please complete [01-Peripheral hardware configuration], [02-openclaw API-KEY configuration], [03-openclaw switching model], [04-OpenClaw prompt words], [05-AI voice interaction configuration], [06-Three dialogue scheme configuration tests] in the
Preparation before usedirectory. If you are currently only using TUI/WhatsApp, you can skip05first. This article assumes that the basic environment has been prepared and only the plant care project itself will be launched.
1. Tutorial Objectives
This article demonstrates OpenClaw's multi-peripheral collaboration capabilities through a plant care scenario.
- Learn how to combine temperature and humidity, OLED, RGB and cameras into a plant care assistant
- Converse with OpenClaw through WhatsApp, TUI, and voice code
2. Hardware preparation
- OpenClaw main control board
- DHT temperature and humidity sensor
- OLED display
- RGB light strip/RGB lamp bead module
- CSI camera
[Optional] AI voice module + speaker- Wiring diagram

3. Software preparation
Code entry that will be used in the tutorial
- Camera photo command:
/home/sunrise/hardware_hal_demo/camera - Visual analysis script:
/home/sunrise/.openclaw/workspace/skills/sunrise-vision/scripts/csi_describe - Voice entrance:
/home/sunrise/voice_to_openclaw/src/main.py
This project essentially does not rely on a single "big project script", but lets OpenClaw orchestrate multiple basic tools:
dhtis responsible for reading the ambient temperature and humidityoledis responsible for displaying care informationrgbis responsible for status reminderscameraandcsi_describeare responsible for observing the appearance of plants
4. Test the basic capabilities of the project
Before starting the current project, please complete a basic dialogue self-test of openclaw tui; if you have not done so yet, please read [06-Three dialogue scheme configuration tests] first. After passing, use TUI to verify the basic capabilities in the project.
Terminal input:
openclaw tui
After confirming that OpenClaw can communicate normally, you can try the following types of commands in sequence:
- Read current temperature and humidity
- Display "Plant OK" on OLED
- Change RGB lights to green
- Take a picture for me
If these individual capabilities can be run through, it means that the main links required for the project have been prepared.
5. Three options for talking to OpenClaw
| Solution | Suitable scenario | Advantages | Suggested positioning |
|---|---|---|---|
| Remote care, classroom demonstrations | Easy access, suitable for remote status viewing | Showcase "remote natural language care" | |
| TUI | Local debugging, project joint debugging | The most direct and easiest to troubleshoot | Run through multiple peripheral links first |
| Voice code | Voice companionship, complete AI experience | Closer to the real assistant experience | As the final demonstration solution |
If the AI voice module + speaker is optional, Feishu dialogue, tui, and WhatsApp dialogue need to broadcast the content of openclaw's reply. You can run the following program on the terminal. The AI voice module dialogue does not need to be run repeatedly
- Modify whether to open broadcast parameters
xxxxxxxxxx/home/sunrise/voice_to_openclaw/.env
xxxxxxxxxxENABLE_TTS=true #This parameter is to control whether to broadcast. After modification, save it and run the following program on the terminal.- Terminal input
xxxxxxxxxxcd ~/voice_to_openclawsource .venv/bin/activatepython -m src.openclaw_session_tts
5.1 WhatsApp solution
For WhatsApp access and robot creation steps, please refer directly to [06-Configuration Test of Three Dialogue Schemes]. This section only retains examples of conversations that would be appropriate for a plant care project.
After successfully creating the robot, you can remotely query the plant status in WhatsApp, for example:
- Take photos to see the current status of plants and perform plant care

5.2 TUI scheme
If you have completed the TUI self-test in Part 6, enter the terminal text dialogue directly:
xxxxxxxxxxopenclaw tuiThen you can directly enter project-related instructions, such as:
- Plant care

5.3 Voice code scheme
xxxxxxxxxxRequires optional ai voice interaction module + speaker
For voice module installation, environment configuration and basic wake-up process, please refer directly to [05-AI Voice Interaction Configuration]. After waking up, you can directly say the control content, such as:
- Help me check the status of the plants and whether it is suitable for watering now

6. Project implementation
Note: The following are all dialogue demonstrations in openclaw tui mode. You can also choose WhatsApp or voice mode to complete it.
6.1 Scenario 1: Environment reading
Experimental goals
Read the current temperature and humidity around the plants to complete the most basic environmental perception.
Effect description
OpenClaw will call DHT to read the current environment data and feedback the temperature and humidity in natural language.
Example instructions
- Read the current temperature and humidity near the plant
- What is the current ambient temperature and humidity?
- Help me check if the area around the potted plants is dry.
6.2 Scenario 2: Status Judgment
Experimental goals
Let OpenClaw give you a brief plant care recommendation after getting the environmental data.
Effect description
In addition to directly reporting values, OpenClaw can also summarize conclusions such as "dry", "hot" and "normal" in a way that is closer to daily language.
Example instructions
- Determine plant status based on current temperature and humidity
- Is it a good time to water?
6.3 Scene 3: Sound and light reminder
Experimental goals
When the environmental conditions are not ideal, use OLED and RGB to give more intuitive reminders.
Effect description
For example, it lights up green when the environment is normal, lights up yellow when it is hot, and lights up red when it is abnormal; at the same time, simple prompt information is displayed on the OLED, so that it is not just "speaking", but has clear peripheral feedback.
Example instructions
- If the environment is normal, the green light will turn on
- If it's too hot, turn on the yellow light and remind me
- Display "Plant Needs Care" on OLED
Expandable gameplay
- Linked buzzer for stronger reminder
- Made into a desktop care status light
- Add scheduled polling and automatic refresh
6.4 Scene 4: Taking photos and observing
Experimental goals
Use a camera to capture the current scene of the plant and let OpenClaw give a brief description.
Effect description
This link is suitable for observing the leaves, flower pot surface or overall growth. The focus of the current tutorial is "take a look and describe it" rather than automatically judging the disease, so it is more suitable for teaching demonstrations and lightweight auxiliary observation.
Example instructions
- Take a photo of the plant
- See how the leaves are doing
- Describe the current plant scene after taking the photo