Deploy OpenViking on Pethost in one click

What happens

1. You sign in to Pethost or make an account, with a passkey, GitHub or Google.
2. No machine yet? You pick a plan, and we prepare one for you. The link waits in your browser until it is ready.
3. New project opens at the app. You fill in what it asks for and click Create project: OpenAI API key.
4. In a minute or two the app is live at its own address with HTTPS. Its secrets are made for it at random, and its data is in the nightly backup.
5. It is a project like any other: its compose.yaml, its .env, its logs and a terminal are in the panel, and your agent can change it, roll it back or restore it.

First steps

Open https://openviking.sam.pethost.app/studio/settings and paste the root key: it is OPENVIKING_ROOT_API_KEY in the project’s .env. Then create an account and a user at /studio/users: the user’s key is what the ov CLI, the SDKs and agents use. Embeddings and summaries go to OpenAI with your key. Data and ov.conf are kept in /app/.openviking.

What it runs

The template is this compose.yaml and the variables it writes into the project’s .env. Pethost runs the file as it is written.

services:
  openviking:
    image: ghcr.io/volcengine/openviking:v0.5.0
    restart: unless-stopped
    environment:
      OPENAI_API_KEY: ${OPENAI_API_KEY}
      OPENVIKING_ROOT_API_KEY: ${OPENVIKING_ROOT_API_KEY}
      OPENVIKING_PUBLIC_BASE_URL: ${URL}
      # The bot needs a user's key of its own; the server runs without it.
      OPENVIKING_WITH_BOT: "0"
      # Written to ov.conf in the volume at the first start only. The server
      # expands the ${...} in it at every start, so a key changed in .env
      # takes effect on a restart.
      OPENVIKING_CONF_CONTENT: |
        {
          "server": {
            "host": "0.0.0.0",
            "port": 1933,
            "root_api_key": "$${OPENVIKING_ROOT_API_KEY}"
          },
          "storage": {
            "workspace": "./data",
            "vectordb": { "name": "context", "backend": "local" },
            "agfs": { "backend": "local" }
          },
          "embedding": {
            "dense": {
              "provider": "openai",
              "api_key": "$${OPENAI_API_KEY}",
              "model": "text-embedding-3-small",
              "dimension": 1536
            }
          },
          "vlm": {
            "provider": "openai",
            "api_key": "$${OPENAI_API_KEY}",
            "model": "gpt-4o-mini"
          }
        }
    volumes:
      - data:/app/.openviking

volumes:
  data:

compose.yamlSee it on GitHub