Edit videos with Continue

PandaStudio from writepanda.ai. Continue from continue.dev (it's a VS Code or JetBrains extension — install from the marketplace).

node --version

Need 18+. Grab it from nodejs.org.

Continue is BYOK — Bring Your Own Key. In its sidebar, click the model picker and follow the prompts to wire up Anthropic, OpenAI, Ollama, or whatever you prefer. Claude Sonnet or GPT-4o-class models work best for tool use.

PandaStudio's automation server is localhost-only and gated by a bearer token. To find your token:

1. Open PandaStudio on your machine.
2. Go to Settings → Automation.
3. Toggle Enable automation server on. A bearer token will appear — copy it.

The token is a random 32-byte secret stored in your OS keychain. It never leaves your machine — agents only need it because the local HTTP server requires it on every request.

The Skill teaches your model (whichever one you use in Continue) how PandaStudio works — commands, async job patterns, editorial defaults. Run this once:

npx skills add kamskans/pandastudio-skills

The tool installs for Continue and any other agents you have. No agent restart needed.

Continue stores config at ~/.continue/config.yaml. Open it from the Continue sidebar (⚙️ → Open config) or directly:

mcpServers:
  - name: pandastudio
    command: npx
    args:
      - "-y"
      - "@writepanda/mcp"
    env:
      PANDASTUDIO_TOKEN: paste-your-token-here

If you already have an mcpServers: list, append the - name: pandastudio entry to it. Save the file — Continue hot-reloads the config.

In the Continue sidebar, switch from Chat to Agent. Then:

• "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."

Continue will pop a confirmation the first time it invokes a PandaStudio tool — accept, and the agent will start chaining commands.