Skip to content
SPECIFICTION
Get listed

Anthropic Sandbox Runtime vs Context Agent Sandboxes

Anthropic Sandbox Runtime

github.com

Context Agent Sandboxes

context.ai

Side by side

FigureAnthropic Sandbox RuntimeContext Agent Sandboxes
Price fromFree$20/mo
Free planYesYes
Free trial——
Open source——
Web—Yes
WindowsYesYes
macOSYesYes
LinuxYesYes
iOS—Yes
Android—Yes
API—Yes
Self-hostedYesYes
Plans published17
Spec score · Sandbox Software9.0 (#5)9.2 (#1)
IntegrationsThe README shows using srt to sandbox Model Context Protocol servers and documents a Java agent for JVM tools on macOS and Linux.Context lists a catalog of 180+ integrations across data, documents, communication, CRM, ITSM, finance, and identity, plus remote MCP servers.
MakerAnthropic describes itself as an AI safety and research company that builds reliable, interpretable, and steerable AI systems.Context is made by Explore Interfaces Inc., a Delaware corporation with an office at 55 2nd Street, Suite 1925, San Francisco, California.
Network controlsNetwork access is denied by default and can be restricted with allowed and denied domain lists; HTTP, HTTPS, and other TCP traffic are mediated by proxies.Administrators can choose open networking, a domain allowlist or workspace-only access, with outbound decisions logged.
PlatformsThe project supports macOS and Linux, and lists Windows support as alpha.The managed sandbox runs Debian Linux, and tasks can also use paired Mac, Windows, or Linux machines as their runtime.
PurposeAnthropic Sandbox Runtime (srt) enforces filesystem and network restrictions on arbitrary processes at the OS level without requiring a container.Each agent task runs in its own sandbox on the customer's cluster under the permissions of the person who requested it.

Plans

Anthropic Sandbox Runtime

  • Anthropic Sandbox RuntimeFree

Anthropic Sandbox Runtime pricing →

Context Agent Sandboxes

  • FreeFree
  • FreeFree
  • Plus$20 a month
  • Plus$20 a month
  • Pro$200 a month
  • Pro$200 a month
  • EnterprisePriced on request

Context Agent Sandboxes 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

Context Agent Sandboxes

Context Agent Sandboxes gives each agent task a separate sandbox on the customer's cluster, using the permissions of the person who requested it. Each run begins in a fresh environment, which is destroyed after an idle period set to 30 minutes by default. Sandboxes run as non-root container pods with capabilities dropped, a seccomp profile, and no cluster service-account token. Administrators can choose open, domain-allowlist, or workspace-only network access, with allowlist decisions logged. In the supervised preset, commands require human approval and connections outside the allowlist prompt for a decision. Drive is not mounted: files pass through a permission-checking gateway, and outputs are pushed explicitly. Credentials are injected at the edge only after authorization. An append-only audit log records commands, files, connections, and permission decisions, including the actor and decision maker. Context lists more than 180 integrations across business categories, plus remote MCP servers. Enterprise sandboxes run on the customer's Kubernetes cluster, with KOTS installation options for EKS or AKS and an air-gapped bundle. Plans include Free at free, Plus at $20 a month, Pro at $200 a month, and custom-priced Enterprise.

Visit context.ai