Skip to main content

Documentation Index

Fetch the complete documentation index at: https://lab.pollack.ai/llms.txt

Use this file to discover all available pages before exploring further.

This project has moved from the spring-ai-community GitHub organization to markpollack. New releases are published under the Maven groupId io.github.markpollack, and Java packages now use the io.github.markpollack namespace. If you previously used org.springaicommunity, update your dependency coordinates and imports to the current values shown below.
A unified API for isolated command execution across multiple backends. Whether you need local process isolation, Docker container security, or cloud-based E2B microVMs, the same Sandbox interface works everywhere. Backends are interchangeable — code written for LocalSandbox works identically with DockerSandbox or E2BSandbox.

​
Backends

LocalSandbox

Local process execution via zt-exec. Fast, no isolation overhead. Good for development and trusted code.

DockerSandbox

Container isolation via Testcontainers. Full filesystem and network isolation. Production-ready.

E2BSandbox

Cloud Firecracker microVMs via E2B. Maximum isolation with MCP support and session reconnection.

​
Core API

try (Sandbox sandbox = LocalSandbox.builder()
        .tempDirectory("test-")
        .build()) {

    // Execute commands
    ExecResult result = sandbox.exec(ExecSpec.of("mvn", "test"));

    if (result.success()) {
        System.out.println(result.stdout());
    }

    // File operations
    sandbox.files()
        .create("pom.xml", pomContent)
        .create("src/main/java/App.java", code)
        .and()    // return to Sandbox
        .exec(ExecSpec.of("mvn", "compile"));
}

​
Module Structure

ModuleBackendDependencies
agent-sandbox-coreLocalSandboxzt-exec
agent-sandbox-dockerDockerSandboxtestcontainers
agent-sandbox-e2bE2BSandboxjackson, awaitility
agent-sandbox-bomBill of Materials—

​
Source

GitHub

Source code — Core, Docker, E2B modules and BOM

​
Used By

  • Agent Judge — agent-judge-exec runs command-based evaluation in sandboxes
  • Agent Client — isolated execution environments for autonomous agents
  • Agent Bench — benchmark execution with configurable isolation level