Skip to main content
Create an agent, start a session, stream its event log, steer it with messages, and receive results by webhook.
Prefer a console? The dashboard does all of this in a UI — create agents and credentials, watch and steer sessions live, and inspect webhook deliveries. The API and SDK below are the same surface, scripted.

​
Core behavior

Built-in runtime supervision

  • Runtime crashes restart automatically
  • Idle sessions hibernate and wake on the next message
  • Hung runs stop cleanly instead of staying stuck

Built-in brain / hands sandboxing

  • Brain: agent loop. Hands: files and commands.
  • Untrusted work stays contained in the hands sandbox
  • Your model key stays in the secret store, never in a sandbox

Live streaming and steering

  • Stream events directly from the browser with a session token
  • Reconnect from any seq without gaps
  • Send follow-up messages without exposing your org key

Webhook delivery

  • Deliver user-level events to your webhook
  • Signed with Standard Webhooks
  • Retried, dead-lettered, inspectable, and redeliverable
Flue uses the same session, event, steering, and webhook APIs on a different execution substrate. Your compiled Flue app is the runtime, each session gets its own Durable Object, and no Linux sandbox is created unless the app explicitly uses ocSandbox.

​
Get started

1

Define an agent

Create a reusable { name, model, prompt, runtime } from your backend, using runtime: "claude" for Anthropic models or "codex" for OpenAI models. Run Managed (credential: "managed", billed to your OpenComputer credits) or pass your own model key. Built-in runtime deployments support isolated revisions, skills, repo push-to-deploy, and pointer rollback. To deploy your own Flue app instead, use the Flue guide. (Agents)
2

Start a session

Start a session with { agent, input }. The agent starts immediately and returns a browser-safe client_token.
3

Watch, steer, get notified

Stream events with EventSource, steer with the client token, and register a webhook when your backend needs push delivery.

​
Architecture

Durable Agent Sessions architecture: your app starts, steers, and streams a durable event-log session; a managed runtime adapter commits events while the brain drives the agent loop and acts through the hands sandbox; the model runs on your key from the secret store, which never enters a sandbox; user-level events are delivered out via your webhook.
The event log is the durable consumer record. Your app starts sessions, streams events, and steers with messages. Built-in runtimes drive the agent loop through brain and hands sandboxes. Flue executes in its Worker and Durable Object, then projects the same public milestone events. Managed model credentials stay outside both execution substrates.

​
When to use sessions

Use sessions for long-running or interactive agents. For a one-shot command, use a sandbox directly.

​
Next steps

Quickstart

Start a session, stream events, and steer it with concise REST examples.

Events

Event shape, visibility levels, cursors, and resume behavior.

Session lifecycle

Statuses, events, results, and limits.

Repos & GitHub

Private repo checkout with GitHub access kept outside the agent sandbox.

Example apps

A repo of examples built on this API.