levain-runtime

Run a Levain agent on your own machine or in your own container image. The platform keeps the recipe, its versions, the run history and the improvement loop; this runtime executes the agent's nodes where your data, tools and dependencies live.

The runtime never accepts inbound connections. It opens one outbound tunnel to the platform and serves node execution over it. Model calls either go through the platform (metered as usual) or use the Claude login present on the runtime host, as configured per runtime.

Install

uv tool install levain-runtime

Set up

# Run nodes directly on this host:
levain-runtime init --mode direct

# Direct mode serving four sessions at once (Linux with bubblewrap):
levain-runtime init --mode direct --sessions 4

# Or run each session in a container built from your own image:
levain-runtime init --mode docker --image ghcr.io/you/agent-runtime:latest

Direct mode links /workspace, /recipes, /sdk and /sandbox to the runtime's home directory (~/.levain/runtime); the command prints and runs the ln commands, with sudo when / is not writable. On macOS the links come from /etc/synthetic.conf: init writes the entries and asks for one restart.

A docker image needs Python 3.12 or later with levain-sdk[review,models] installed, plus whatever your recipes import.

Register and run

export LEVAIN_API_KEY=...   # a workspace API key
levain-runtime register --name workstation --model-auth local
levain-runtime up

register creates the runtime in your workspace and stores its credentials here. If the runtime was created elsewhere (the Levain app or API), pass the credentials it returned instead: levain-runtime connect --credentials runtime-credentials.json.

up starts the local node server, the tunnel client and a heartbeat so the platform can show whether the runtime is online. It fetches the current tunnel settings from the platform on every start. levain-runtime status prints the configuration and the sessions on this runtime.

How it works

Each agent session gets a workspace directory under the runtime home (sessions/<id>/workspace, or agents/<id>/workspace for agents with a persistent workspace). The platform delivers the recipe and SDK into /recipes and /sdk, then runs each node as a short-lived process with the session's environment. Everything a node prints is streamed back and lands in the run's logs on the platform.

Direct mode serves one session at a time by default: /workspace points at the active session. With --sessions N it serves up to N at once, each node running under bubblewrap with its session's folders mounted at /workspace, /recipes/active and /sdk/active; the real workspace path is in LEVAIN_HOST_WORKSPACE for tools outside the sandbox such as Docker. Docker mode starts one container per session and has no such limit.