Skip to main content
The open-source server runs without a Polpo Cloud account. The repository requires Node.js 20+ and pnpm through Corepack.

Build the server

The root pnpm dev script only watches TypeScript; it does not start an HTTP server.

Create a local project

The server reads a project from WORK_DIR. Create a workspace with these files:
.polpo/polpo.json
.polpo/teams.json
.polpo/agents.json

Start the server

From the cloned Polpo repository:
The server listens on http://localhost:3890 by default. Provider credentials can also go in workspace/.polpo/.env. Check the server:
Call chat completions at the OpenAI-compatible path:

Use the SDK

Authentication is disabled when both POLPO_API_KEY and POLPO_API_KEYS are unset. See Self-hosting before exposing the server to a network.

Run the dashboard locally

The open-source repository includes a single-tenant Next.js host for the v2 runtime views. In a second terminal:
Open http://localhost:3000. The app proxies requests server-side, so the runtime API key is not embedded in the browser bundle. The reusable views are published separately as @polpo-ai/dashboard for custom hosts.

Move the configuration to Cloud

From the project workspace, authenticate and deploy. When the local config has no Cloud project ID, the deploy command resolves or creates the target project interactively:
Use polpo link --project-id <uuid> only when you intend to bind to an existing project and pull its current remote resources before deploying. The CLI can offer to upload recognized local provider keys during deploy. See Deploy and Model Gateway.