I forked a live AI agent three ways, and every copy came up with its web server already running

Description and use

The experiment demonstrated that DigitalOcean Managed Agents allow checkpointing, forking, and rollback of a microVM, preserving running processes and files. Three forks started with the same server PID, and rollback restored a killed process with the same PID.

Problem

How to preserve and explore an AI agent’s state efficiently in a disposable sandbox environment.

Outcome

Forking a checkpointed session preserves all running processes and file state, allowing parallel exploration from the same exact state. Rollback restores killed processes with identical PIDs, confirming memory state is retained.

Workflow

• 1. Start a session and run a Python HTTP server inside the sandbox.
• 2. Build a single‑file web dashboard with an AI agent (OpenCode, DeepSeek v4 Pro).
• 3. Checkpoint the session (25.2 s).
• 4. Fork the checkpoint three times (15.3 s).
• 5. Verify each fork starts with the same PID 593 and serves the same index.html.
• 6. Give each fork a different design brief and observe the resulting dashboards.
• 7. Kill the server and delete the app directory in the parent session.
• 8. Roll back the parent session to the checkpoint (5.6 s).
• 9. Confirm the killed process restarts with PID 593 and serves the original page.

Evidence

With the dashboard working, I checkpointed the session and forked it three times from that checkpoint:

Source

fork1: PID 593 | local GET -> 200 | index.html 6695 bytes

Source

rollback call: 5.59s until READY: 6.04s
app dir: index.html
server : PID 593
GET : 200

Source