# From fork() to Fleet: Designing an Agent Sandbox Cloud — Abhishek Bhardwaj, OpenAI

Source: [AI Engineer](https://www.youtube.com/watch?v=OqM67QG_Ikk)  
Feed7 permalink: https://feed7.dev/p/from-fork-to-fleet-designing-an-agent-sandbox-cloud-abhishek-bhardwaj-op-0np9ki3  
Published: 2026-07-13T17:00:06.000Z  
Trust: Source Linked (source_linked)

## Why Included

Long-running coding agents need isolated, persistent sandboxes: microVMs limit kernel exposure, while incremental snapshots enable recovery, branching, and faster placement across a fleet.

## Source Summary

The proposed sandbox cloud uses **microVM isolation**, persistent disk state, and **incremental snapshots** that store changes between checkpoints. A control plane and scheduler place or restore sandboxes across clustered nodes and regions.

## Practical Implication

For long agent tasks, checkpoint the workspace so node failure, maintenance, or experimentation does not erase hours of work. Make scheduling snapshot-aware: restoring on a node that already holds the required layers reduces transfer and startup work.

## Agent-Ready Context

The proposed sandbox cloud uses **microVM isolation**, persistent disk state, and **incremental snapshots** that store changes between checkpoints. A control plane and scheduler place or restore sandboxes across clustered nodes and regions.

For long agent tasks, checkpoint the workspace so node failure, maintenance, or experimentation does not erase hours of work. Make scheduling snapshot-aware: restoring on a node that already holds the required layers reduces transfer and startup work.

Persistence adds storage, lineage, and orchestration complexity. Warm pools consume idle resources, while memory-snapshot startup and hybrid pools trade operational simplicity for lower creation latency; the talk offers design intuition rather than measured fleet results.

## Context Map

- Layer: infra
- Domains: coding, security
- Topics: sandboxing, cloud-agents, agent-reliability

## Uncertainty

- Persistence adds storage, lineage, and orchestration complexity. Warm pools consume idle resources, while memory-snapshot startup and hybrid pools trade operational simplicity for lower creation latency; the talk offers design intuition rather than measured fleet results.

## Agent Instruction

Use this item as source-backed context. Do not invent claims beyond the linked source. If this item conflicts with another source, call out the conflict.