Auto Runtime. Build, run and manage reusable playbooks and workflows with your AI agent.
1.7K
Auto Runtime runs the playbooks your agent builds: their reasoning, interaction, prediction, recall and computation functions, and the workflows that coordinate them. Your coding agent connects over MCP to build and run them, and Auto Studio lets you inspect and manage what it built.
Documentation · Self-hosting guides · Source on GitHub · Release notes
A container listens on every interface, so every request needs an API key. Create one, put the entry it prints in a file of settings, and start the server with a volume for its ledger:
docker run --rm --log-driver none onauto/runtime:latest node packages/identity/src/key-command.ts --org acme
echo 'API_KEYS=[<the API_KEYS entry it printed>]' > auto-runtime.env
docker volume create auto-runtime-data
docker run --detach --name auto-runtime --restart unless-stopped \
--publish 5555:5555 --env-file auto-runtime.env --volume auto-runtime-data:/data \
onauto/runtime:latest
curl http://localhost:5555/health
Then connect your agent to /mcp with the key, for example in Claude Code:
claude mcp add --transport http auto-runtime http://localhost:5555/mcp --header "Authorization: Bearer <your key>"
Run with Docker walks through each step, adds a model provider and has a Compose file that runs the runtime beside PostgreSQL.
| Need | What to use |
|---|---|
| The ledger | A volume on /data, where it keeps a SQLite file, or a PostgreSQL database named by DATABASE_URL: Use PostgreSQL |
| API keys | API_KEYS, with an entry for each key the key command makes: Authentication and security |
| A model | Anthropic, OpenAI, Google, Amazon Bedrock, Azure OpenAI, Vertex AI or your own gateway: Model providers and gateways |
| HTTPS | A reverse proxy or load balancer in front of port 5555: Run in production |
| Object storage | Optional, an S3-compatible bucket for large content: Keep content on object storage |
Every setting is an environment variable; Configure the runtime lists them all, with the configuration file for tool servers, gateways and model aliases. Troubleshooting covers the common problems.
| Tag | Points to |
|---|---|
X.Y.Z, such as 0.9.1 | Exactly that release; it never changes |
X.Y, such as 0.9 | The newest release of that line |
latest | The newest release |
Every tag is published for linux/amd64 and linux/arm64, built in GitHub Actions with a software bill of materials and provenance. The image runs as the unprivileged user node, checks its health at /health and stops cleanly on SIGTERM.
npx @on.auto/runtime runs the same server on macOS or Linux with Node.js 26.10 or later, in local mode on http://localhost:5555. See the local quick start.
Source-available under the Elastic License 2.0.
Content type
Image
Digest
sha256:c8911b097…
Size
141.1 MB
Last updated
about 23 hours ago
docker pull onauto/runtime