A local-first AI agent skill for discovering, authenticating, and capturing snapshots from Tapo cameras via RTSP and ONVIF.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install tapo-camera
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install tapo-camera using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Tapo Camera?
The Tapo Camera skill enables AI agents to interface directly with Tapo smart cameras within a trusted local network. By prioritizing local-first RTSP and ONVIF protocols, it bypasses cloud dependencies for core tasks like snapshot capture and device status verification. This implementation focuses on security and privacy, ensuring that camera credentials and media frames remain within the user's controlled environment while providing a robust framework for local device discovery using Openclaw Skills architecture.
By leveraging maintained local tooling, this skill allows for high-fidelity interaction with Tapo hardware without compromising the user's privacy or exposing sensitive streams to external cloud services. It is designed for developers and power users who require deterministic camera control within an agentic workflow.
Tapo Camera Use Cases
- Verifying camera reachability and status on a local network.
- Capturing still frames (snapshots) for AI inspection or security logging.
- Automating local camera discovery and capability mapping.
- Integrating Tapo hardware into private home automation workflows without cloud exposure.
How Tapo Camera Works
- The agent identifies the camera host and verifies ownership within the local network segment.
- It uses python-kasa to authenticate and retrieve device-specific capabilities and module presence.
- Based on the specific model, the agent selects the appropriate protocol, such as RTSP or ONVIF.
- A single-frame JPEG is captured using ffmpeg from the local stream and saved to an explicit destination.
- The agent logs the session details, capture paths, and success metrics for deterministic future access.
Tapo Camera Setup
Ensure you have python3 and ffmpeg installed on your system. Then, install the required python library and CLI tool:
pip install python-kasa
For macOS users using Homebrew, ensure ffmpeg is available:
brew install ffmpeg
Configure your Tapo camera credentials as environment variables to keep them secure and out of your persistent history:
export TAPO_CAMERA_USERNAME='your_rtsp_username'
export TAPO_CAMERA_PASSWORD='your_rtsp_password'
Tapo Camera Data Schema & Taxonomy
The skill organizes its persistent data and logs within the ~/tapo-camera/ directory to facilitate long-term memory and troubleshooting across Openclaw Skills.
| File/Folder | Description |
|---|---|
memory.md |
Activation boundaries, preferred defaults, and trust limits. |
cameras.md |
Inventory of hostnames, labels, model notes, and stream capabilities. |
sessions/ |
Dated logs of capture attempts and successful workflow paths. |
captures/ |
Directory containing user-approved local still images. |
incidents.md |
Log of authentication, network, and protocol-specific failures. |
Tapo Camera Advanced Features
- Multi-protocol support (RTSP/ONVIF) for maximum compatibility across various Tapo models.
- Automated credential injection via environment variables or secret managers to prevent secret leakage in logs.
- Local-first fallback logic designed specifically for hub-connected or battery-powered devices.
- Structured incident logging to diagnose firmware regressions or network configuration changes.
- Integration ready for other Openclaw Skills such as ffmpeg for advanced media processing or photos for organization.
SKILL.md
Loading
Related Openclaw Skills
AI Traffic Tracking
A technical framework for isolating and analyzing traffic originating from AI search engines and chatbots within standard analytics platforms.
opc-cashflow-manager
A survival-focused cash flow decision system for solo founders that provides probability-weighted forecasting and runway alerts.
Safe Exec
A specialized security skill designed to analyze script intent and detect malicious behavior before code execution.
CogDx - Cognitive Diagnostics
CogDx provides external cognitive verification for AI agents to detect biases, audit reasoning, and ensure mathematical calibration of confidence levels.
A-Share Daily Market Video Report
A professional automation skill that transforms A-share market data and financial news into high-quality, AI-analyzed review videos.
German Social Law & Labor Assistant
A specialized assistant for navigating German labor law, Citizen's Benefit (Bürgergeld), and vocational retraining through automated legal research and document generation.
Featured*
