Runtime
OfficialRuntime
The SDKs, CLI, MCP server and agent integrations for Runtime: sandboxes for AI agents. Each sandbox is a Firecracker microVM with its own Linux kernel, started from one call.
npm install withruntime # TypeScript SDK, the `runtime` CLI and the MCP server
pip install withruntime # Python SDK, sync and asyncimport { Sandbox } from "withruntime";
await using sbx = await Sandbox.create();
const result = await sbx.exec("python3 -c 'print(6 * 7)'");
console.log(result.exitCode, result.stdout);from withruntime import Sandbox
with Sandbox.create() as sbx:
result = sbx.exec("python3 -c 'print(6 * 7)'")
print(result.exit_code, result.stdout)The client reads RUNTIME_API_KEY, or the connection npx withruntime login
saved on this machine. A new account starts on a free trial with no card. The
quickstart takes it from there.
What is here
Path | What it is |
| The TypeScript SDK, the |
| The Python SDK: |
| LangChain and Deep Agents sandbox backend |
| The Go, Java and Ruby SDKs |
| Pydantic AI and Google ADK integrations |
| Skills, rules and MCP settings for coding agents |
| The guides served at withruntime.com/docs, which the SDK tests check samples against |
Related MCP server: agent-sandbox-mcp
Documentation
TypeScript and Python
Frameworks, and moving from E2B or Daytona
Tests
bun test in packages/cloud-sdk and python3 -m unittest discover -s tests
in sdks/python run here as they are. The suites that start Runtime's API
server in-process, including all of the Go, Java and Ruby tests, run in
Runtime's main repository before each release.
Contributing
Each release copies the SDKs here from Runtime's main repository, so each commit here is one copy, named after the versions in its source; a copy made before those versions reach npm and PyPI says so. Issues are welcome. A pull request is reviewed here and carried into the next release with its author credited.
License
Apache-2.0. See LICENSE.
Related MCP Connectors
Persistent Linux microVMs for agents: root, internet, sub-second resume and a public URL.
Remote Linux boxes for coding agents: Docker, a browser, screenshots, logs, human takeover.
- mcp-serverOAuthai.cdbx
Build Apps and run code in 30 languages — sandboxed, with persistent sessions for agent loops.
Sovereign Agent OS — Persistent Memory, Governance & Compliance for AI Agents.
Related MCP Servers
- AlicenseAqualityCmaintenanceRun AI agents in VM-isolated sandboxes on your Mac.151MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to create, manage, and execute code in isolated Firecracker microVM sandboxes via the MCP protocol, with support for sandbox lifecycle and file operations.3Apache 2.0
- AlicenseNot gradedqualityAmaintenancePersistent, secure LXC sandbox environments for AI agents with native MCP support.288Apache 2.0
- AlicenseNot gradedqualityAmaintenanceEnables time-travel debugging for AI agent sandboxes using Firecracker microVMs, with tools for code execution, file operations, and VM snapshot/restore via MCP.63 PyPI1MIT