Background agents

Close the laptop. The agent keeps working.

AgentSky runs your agent in a persistent cloud sandbox that retains files, state, and session history across supported pause, restart, and image-update flows. This runtime has completed 40,835 tasks across 10 agent stacks without a local machine to keep alive. Any authorized teammate can resume from web, Slack, Telegram, or the API.

Agents lose their context and work when the machine that started them goes offline.

Choose AgentSky when

Teams handing off long-running work across people or supported channels while the agent's cloud computer and session stay available.

Choose another approach when

Use a local agent for short device-bound work, or a self-hosted runtime when infrastructure ownership, data residency, or custom images are mandatory.

How it works

One job. One complete cloud agent.

01

Job transfers to a persistent cloud sandbox

Start a session from the Playground, the API, or the sky CLI. The agent owns a cloud computer from the first message — not dependent on your laptop or local connection.

02

Sandbox outlasts any single session

Files, tools, and session history remain available through supported pause, restart, and image-update flows. Recovery returns the agent to its persisted work state without rebuilding the runtime by hand.

03

Full history resumes from any channel

Resume from web, Slack, Telegram, or the API. The full session history is in place — any team member can continue, not just whoever started the session.

You choose

  • Task and instructions
  • Agent harness and model
  • Which channel to resume from

AgentSky runs

  • Persistent cloud sandbox
  • Files, state, and history
  • Recovery on restart

Typical stack: Hermes + DeepSeek V4 Pro

See the agent

Agent Hosting

Teams bring their existing agent and model subscription to AgentSky. The persistent sandbox, automatic recovery, and session history run underneath — no fleet to operate, no sessions to restart manually.

Evidence scope: A product capability description, not a published SLA or independent reliability benchmark; validate recovery requirements for your workload.

See capability details

Close the laptop. The agent keeps working.

Try in Playground