2026 archives
Engineering articles in publication order, newest first.
AI Sandbox: How It Works, Security Boundaries, and Agent Use Cases
A developer's guide to AI sandboxes: isolate agent code, choose a runtime, compare platforms, and check what survives pause and resume with a reproducible filesystem example.
When an AI Agent Breaks Its Sandbox, Stay in Control
Keep control when an AI agent breaks its environment. Sandbox0 manages recovery from outside the sandbox, preserving committed files and your recovery choices.
Why Sandbox0 Is a Good Fit for Personal Agent Cloud Computers
Personal agents need a computer they can keep coming back to. Sandbox0 combines a persistent, automatically growing root filesystem with incremental checkpoints and on-demand compute to make that practical at scale.
A Root Filesystem That Grows with Your Agent
Sandbox0 now grows the writable RootFS online, with sparse devices up to 64 TiB and incremental background commits. How it works, what survives a worker change, and how it compares with sandbox disks and mounted volumes.
AI Sandbox Pricing: Compute, Storage, and Paused Time
Sandbox0 Cloud charges for running compute and retained incremental storage. Shared base images and platform recovery retention are excluded; pausing stops compute charges.
Moving a Running AI Agent Sandbox Between Nodes
How Sandbox0 moves running process state between compatible workers using stock gVisor, block-COW storage, and peer-to-peer transfer—and what our roughly 3.5-second benchmark measures.
A Sandbox Is Not a Container: Inside Sandbox0's New Nomad Architecture
Sandbox0 now separates durable sandbox identity and encrypted block-COW RootFS state from disposable Nomad workers. This post explains the carrier pool, claim-time resource leases, stock gVisor isolation, and failure boundaries behind the redesign.
How We Cut gVisor Metrics CPU by 72% at 424 Sandboxes
At high sandbox density, every CRI stats request launched a runsc subprocess before calling an existing gVisor control RPC. This post explains how Sandbox0 removed that process boundary, kept the same metrics contract, and reduced average node CPU from 60.68% to 16.70% in a matched production comparison.
Vercel Eve Sandbox Backend: Run Eve Agents on Sandbox0
Vercel Eve makes the sandbox backend pluggable. This guide shows how to use Sandbox0 as an Eve SandboxBackend with @sandbox0/eve, including prewarm snapshots, durable session metadata, file and command APIs, and network policy boundaries.
Initialize Once, Claim Many: Custom AI Agent Sandboxes on Sandbox0
Custom AI agent environments do not always need another template artifact. Sandbox0 rootfs snapshots and claim-time snapshot IDs let teams start from a compatible template, initialize the writable filesystem once, and claim fresh running sandboxes from that state.
Docker in Sandbox: Run Docker Inside an AI Agent Sandbox with Sandbox0
Sandbox0 Docker in Sandbox lets AI agents run Redis, Postgres, Docker builds, and containerized test workflows inside an isolated sandbox without depending on the host Docker daemon.
MCP Tool Access Control: Restrict Which Tools AI Agents Can Call
MCP makes it easy to connect agents to tools, but production teams need runtime enforcement for which tools can actually execute. Sandbox0 Protocol Controls add MCP tool allowlists and denylists at the sandbox network boundary.
Claude Code SDK Deployment Modes: Ephemeral, Long-Running, and Hybrid
Anthropic now calls it the Claude Agent SDK, but many developers still search for Claude Code SDK. This post separates three deployment modes from a second, independent decision: whether the Claude runtime lives in the same environment as your app or behind a control and execution boundary.
AI Hallucinated Links: Building a Semantic 404 Resolver for AI Agents
AI agents often request plausible-but-wrong URLs like /docs/self-hosting or /docs/deploy/single-cluster and land on a 404 page. This post explains why static redirect tables do not scale, and how to build a local semantic 404 resolver that maps hallucinated links to the most likely canonical page without creating soft 404s.
API Key Security for AI Agents: How to Keep Secrets Out of the Sandbox
The standard advice for AI agent API key security is to use a local proxy that swaps fake tokens for real ones. Sandbox0 goes further: credentials are injected at the kernel network layer, so the agent process never holds a token — real or phantom.