The deployable demo behind the Daytona cookbook recipe.
A minimal CopilotKit Built-in Agent app whose only added capability is a runCode server tool that executes
Python / TypeScript / JavaScript inside an isolated Daytona sandbox and streams the
result back to the chat — with a custom useRenderTool card (fixed-height streaming code pane with
syntax highlighting and a fixed-height result pane).
app/api/copilotkit-single/route.ts— the recipe'srunCodetool wired into aBuiltInAgentoncreateCopilotEndpointSingleRoute. Pure recipe code (Python/TS/JS viadaytona.create({ language })).app/page.tsx—CopilotKitProvider+CopilotSidebar+ auseRenderTool({ name: "runCode" })renderer usingreact-syntax-highlighter(Prism +vscDarkPlus, mirroring@copilotkit/react-ui's ownCodeBlock).- A system prompt that tells the agent the tool result is rendered directly to the user, so it doesn't restate stdout in chat text.
- Node 18+
- An OpenAI API key (
OPENAI_API_KEY) — the recipe defaults toopenai:gpt-5.4-mini, overridable via theMODELenv var. - A Daytona API key (
DAYTONA_API_KEY) — create one in the Daytona dashboard.
npm install
echo "OPENAI_API_KEY=sk-…" > .env.local
echo "DAYTONA_API_KEY=…" >> .env.local
npm run dev # http://localhost:3000Open the page, click into the sidebar chat, and ask something like:
Run a Python snippet that prints the first 10 Fibonacci numbers.
Run JavaScript that logs Date.now().
- This is a standalone npm project — intentionally not in the monorepo's
pnpm-workspace.yaml.npm installhere installs against published@copilotkit/*@1.58.0, which is the same surface the recipe targets. new Daytona()throws at module load ifDAYTONA_API_KEYis missing, so the app won't boot without it. That's by design — the key is required, not optional.- For arbitrary languages beyond Python/TS/JS, swap
sandbox.process.codeRunforsandbox.process.executeCommand(...)and optionally use a custom DaytonaImagewith the toolchain preinstalled. See the recipe's Going further section.