Skip to content
SPECIFICTION
Get listed

Anthropic Sandbox Runtime vs E2B

Anthropic Sandbox Runtime

github.com

E2B

e2b.dev

Side by side

FigureAnthropic Sandbox RuntimeE2B
Price fromFree$150/mo
Free planYesYes
Free trial—Yes
Open source—Yes
Web—Yes
WindowsYesYes
macOSYesYes
LinuxYesYes
API—Yes
Self-hostedYesYes
Plans published13
Spec score · Sandbox Software9.0 (#5)9.1 (#4)
IntegrationsThe README shows using srt to sandbox Model Context Protocol servers and documents a Java agent for JVM tools on macOS and Linux.Listed integrations include OpenAI Agents SDK, Claude Code, Codex, CrewAI, Agno, Mastra, Google ADK, LangChain, Vercel AI SDK and MCP servers.

Plans

Anthropic Sandbox Runtime

  • Anthropic Sandbox RuntimeFree

Anthropic Sandbox Runtime pricing →

E2B

  • HobbyFree
  • Pro$150 a month
  • EnterprisePriced on request

E2B pricing →

In their own words

Anthropic Sandbox Runtime

Anthropic Sandbox Runtime (srt) is a free, open-source research preview that applies filesystem and network restrictions to processes at the operating-system level, without requiring a container. It can be used as a CLI tool or library to sandbox agents, local MCP servers, bash commands and other processes. Filesystem writes and network access are denied by default, with configuration options to allow paths and domains. The project documents macOS, Linux and Windows support, using sandbox-exec, bubblewrap or a dedicated local sandbox account with Windows Filtering Platform and filesystem ACLs, respectively. Windows is marked alpha. Install it from npm with `npm install -g @anthropic-ai/sandbox-runtime`. Linux requires bubblewrap, socat and ripgrep; macOS requires ripgrep, and Windows needs a one-time elevated setup step. On macOS, srt can provide real-time alerts from the system sandbox violation log. Linux bubblewrap has no built-in violation reporting, and Linux network filtering relies on proxy environment variables, which some programs may ignore. The preview is developed for Claude Code; its APIs and configuration formats may evolve.

Visit github.com

E2B

E2B provides isolated Linux machines for AI agent sessions, with infrastructure managed by E2B or deployed in a customer’s cloud. Each session runs in its own Firecracker microVM and kernel, without sharing filesystem or memory with another customer’s sandboxes. An API covers execution, networking, storage, secrets, observability, and lifecycle management. The Code Interpreter SDK runs Python or JavaScript and can return charts, tables, and images; Desktop supplies screen, mouse, keyboard, and live streaming for computer-use agents. Listed integrations include CrewAI, Agno, Mastra, OpenAI Agents SDK, Google ADK, LangChain Deep Agents, and Vercel AI SDK. E2B Cloud is available in US, EU, and APAC regions. Enterprise BYOC can place sandboxes in a customer’s AWS, Google Cloud, or Azure account. The runtime is Apache-2.0 licensed and self-hostable. Hobby is free, with a one-time $100 usage credit, sessions up to one hour, and 20 concurrent sandboxes. Pro costs $150 a month plus usage costs.

Visit e2b.dev