Edit videos with OpenClaw

PandaStudio from writepanda.ai. Launch it once so the local credentials file is written — that's all the setup PandaStudio needs. Then install OpenClaw:

npm install -g openclaw@latest

Run openclaw onboard --install-daemon once to set up the gateway and connect your first chat channel. Verify with openclaw --version.

OpenClaw ships MCP as an opt-in extra. Install it once:

cd ~/.openclaw/openclaw-agent && uv pip install -e ".[mcp]"

Open PandaStudio, go to Settings → Local automation, and click the three buttons in this order:

• Install to PATH — puts pandastudio-mcp on your $PATH so OpenClaw can launch it.
• Connect agents → OpenClaw → Connect — registers PandaStudio as an MCP server with OpenClaw for you.
• Install Skill — copies the official PandaStudio Skill into OpenClaw (and Claude / Codex / Hermes) so the agent knows what to do, not just how to call it.

Then reload OpenClaw so the new server registers, and confirm it started:

openclaw mcp reload
openclaw mcp doctor pandastudio --probe

Prefer the terminal? Same registration via openclaw mcp add pandastudio --command pandastudio-mcp.

From any of OpenClaw's connected channels (Slack, Telegram, WhatsApp, Discord, the terminal), message OpenClaw:

• "Open my latest recording, transcribe it, remove filler words and silences, then export an MP4."
• "Create a new 9:16 project, import the file at ~/Recordings/launch.mov, add bold captions, and preview it."
• "List all my projects from this week and tell me which one is longest."

Because OpenClaw runs locally and has memory + scheduling, you can also set up recurring jobs ("every Friday, transcribe my new recordings and draft titles for each").