Run multiple isolated agents in a single Sandbox
Vercel Sandbox can now isolate agents as Linux users while exposing selected files through a shared group directory. This gives multi-agent harnesses a simpler permission boundary.
The **@vercel/sandbox SDK** now supports multiple Linux users and groups. Each agent gets a **private home directory**; users cannot read, write, or list one another’s files, while a **shared group directory** supports collaboration.
Create one user per agent and expose only the workspace they need through a group. This makes coder-reviewer or other multi-agent roles easier to separate without provisioning a sandbox for each role.
The **@vercel/sandbox SDK** now supports multiple Linux users and groups. Each agent gets a **private home directory**; users cannot read, write, or list one another’s files, while a **shared group directory** supports collaboration. Create one user per agent and expose only the workspace they need through a group. This makes coder-reviewer or other multi-agent roles easier to separate without provisioning a sandbox for each role. The boundary is user and group permissions inside one Sandbox. The material does not claim separate kernels, resource quotas, or protection from vulnerabilities that cross operating-system user boundaries.
This adds a practical least-privilege layout for cooperating agents inside one sandbox: private homes for role separation and a deliberately shared workspace for handoffs. It narrows the meaning of isolation in prior sandbox guidance, because Unix users reduce accidental cross-agent file access but do not provide the separate-kernel boundary, quotas, or recovery properties associated with stronger sandbox architectures.