SesameSesame

Sandboxes

Sandboxes are used to run agent tasks in isolated environments.

Sesame uses sandboxes to isolate agent task execution. Each sandbox provider offers different tradeoffs between security, performance, and ease of setup.

Security Overview

In addition to provider-level isolation, Sesame supports OS-level sandbox security via @anthropic-ai/sandbox-runtime. This adds filesystem and network restrictions regardless of which provider you use.

Security LayerProtectionAvailability
Provider IsolationProcess/container separationAll providers
Sandbox SecurityFilesystem + network restrictionsmacOS, Linux

Sandbox security is enabled by default on supported platforms. Configure it at /admin/sandbox or via SANDBOX_SECURITY_ENABLED.

What Sandbox Security Provides

  • Filesystem restrictions: Agents can only write to the project directory and /tmp. Sensitive paths like ~/.ssh and ~/.aws are blocked.
  • Network restrictions: Only agent-specific API domains are allowed (e.g., api.anthropic.com for Claude). Admins can configure additional allowed/denied domains.
  • Violation monitoring: Blocked access attempts are logged and streamed to the UI in real-time.

See Settings > Sandbox Security for configuration details.

Runtime & Dependency Management

Sesame uses mise to automatically detect and install the correct runtime versions and dependencies for each project.

FeatureWhat It Does
Runtime versionsReads .nvmrc, .node-version, .python-version, .tool-versions, mise.toml
DependenciesAuto-runs npm install, pip install, bundle install, etc. based on lockfiles
IsolationEach sandbox gets its own mise installation

This means agents work with the exact versions specified in the project, without manual setup.

See How It Works > Mise Integration for technical details on how this works.

Sandbox Providers

Comparison

ProviderIsolationSecuritySetupPerformanceUse Case
FilesystemProcess+ Sandbox SecurityNoneFastDevelopment, trusted environments
DockerContainer+ Sandbox SecurityDocker requiredFast (with sandbox image)Production, multi-tenant
VercelCloud microVMFullAPI credentialsFastVercel hosting, cloud-native
DaytonaCloud sandboxFullAPI keyFastCloud development, flexible resources

The Vercel provider requires ports to be declared at sandbox creation time. See the Vercel Sandbox docs for configuration details.

The Docker provider uses the official sesame-sandbox image by default, which comes pre-loaded with mise, common runtimes (Node.js, Python, Go, Rust, Ruby, Bun), and all agent CLIs for fast task startup.

On this page