Agent Switchboard

Browse Agents

Task

I need to run code in a sandbox

Remove task

Run code an agent writes in an isolated container or microVM, away from your machine.

Picked from listings that mention sandbox, code execution, isolated or microvm in their name, description, tags or skills; those in Infrastructure & Ops or Code & DevTools, or with API access, rank higher. About this task →

43 agents fit this task

20 Official · all Verified · 14 No auth needed · 32 API · 15 MCP · 34 CLI · 1 Extension

Vercel Sandbox

API · CLI

Runs untrusted or agent-generated code in isolated Firecracker microVMs on Vercel, with snapshots, persistent…

VerifiedOfficialby Vercel · Browser & Computer Use, Infrastructure & Ops · 5 skills · Bearer Token

CubeSandbox

API

Runs self-hosted, KVM-isolated sandboxes for agent code execution behind an E2B-compatible API, with snapshots…

VerifiedOfficialby Tencent Cloud · Infrastructure & Ops, Security · 5 skills · No auth

Perplexity SPACE

API · CLI

Runs agent and user code in isolated Firecracker microVM sandboxes on your own infrastructure, with an HTTP API to…

VerifiedOfficialby Perplexity · Infrastructure & Ops, Security · 4 skills · Bearer Token

Sandbox0

API · CLI

Runs agent-generated code in managed cloud sandboxes with pause/resume and persistent root filesystems, through an…

Verifiedby Sandbox0 · Infrastructure & Ops, Code & DevTools · 3 skills · API Key

OpenSandbox

API · MCP · CLI

Runs AI-agent workloads in isolated Docker or Kubernetes sandboxes, exposing sandbox lifecycle, command, filesystem…

Verifiedby OpenSandbox Group · Infrastructure & Ops, Code & DevTools · 5 skills · API Key

Docker Sandboxes

API · CLI

Disposable, isolated container sandboxes for running untrusted agent-generated code, with filesystem and network…

VerifiedOfficialby Docker · Infrastructure & Ops, Security · API Key

Agent Substrate

API · CLI

Runs agents in secure-by-default microVM sandboxes on GKE, delivering high sandbox density and sub-second resume…

Verifiedby Google Cloud · Infrastructure & Ops, Orchestration · 3 skills · No auth

BoxLite

API · CLI

Embeds hardware-isolated micro-VM sandboxes that run any OCI image with persistent state, via Python, Node, Go, and…

Verifiedby BoxLite · Infrastructure & Ops, Security · 4 skills · No auth

DigitalOcean Managed Agents

API · CLI · MCP

Runs agent harnesses like Claude Code, Codex CLI, and LangGraph in isolated cloud microVM sessions, with governed…

VerifiedOfficialby DigitalOcean · Infrastructure & Ops, Orchestration · 4 skills · Bearer Token

NVIDIA OpenShell

CLI · API

Runs autonomous agents in isolated sandboxes with kernel-level policy enforcement over files, syscalls, and network…

VerifiedOfficialby NVIDIA · Security, Infrastructure & Ops · 4 skills · No auth

Codex CLI

CLI · MCP

Runs a coding agent locally in the terminal, editing files and executing commands inside an OS sandbox with…

VerifiedOfficialFeaturedby OpenAI · Code & DevTools, Orchestration · 5 skills · OAuth 2.0

Microsoft Execution Containers (MXC)

API · CLI

Runs untrusted model output, plugins, and tools in policy-driven sandboxes on Windows, Linux, and macOS through Rust…

VerifiedOfficialby Microsoft · Security, Infrastructure & Ops · 4 skills · No auth

context-mode

MCP · CLI

Keeps raw tool output out of coding agents' context by running code and commands in a sandbox, indexing results for…

Verifiedby mksglu · Code & DevTools, Memory & State · 4 skills · No auth

DeepSeek Harness

CLI · API

Runs coding agents on a plugin-composed harness where models, tools, skills, sessions, sandboxes, storage, and the UI…

VerifiedOfficialFeaturedby DeepSeek · Orchestration, Code & DevTools · 3 skills · API Key

OpenHands

API · CLI

Software engineering agent platform — runs in sandboxed Docker containers, edits code, runs tests, fixes bugs, and…

Verifiedby All Hands AI · Code & DevTools, Browser & Computer Use · 3 skills · Bearer Token

E2B

API · CLI

Secure cloud sandboxes for AI agents to run code. Supports Python, JS, and shell. Persistent filesystem, network…

Verifiedby E2B · Browser & Computer Use · 5 skills · API Key

Google AX

API · CLI

Runs sandboxed agentic tasks at cluster scale from declarative YAML Task, Workspace, and Model manifests on Agent…

VerifiedOfficialFeaturedby Google · Orchestration, Infrastructure & Ops · 4 skills · No auth

OpenAI Agents API

API · MCP

Run OpenAI's Codex harness as a managed service — durable sessions that survive restarts, hosted or self-hosted…

VerifiedOfficialFeaturedby OpenAI · Orchestration, Infrastructure & Ops · 4 skills · API Key

pi pod

CLI

Runs pi coding-agent sessions in isolated remote sandboxes on a server you host, and lets you attach from a terminal…

Verifiedby pi pod · Infrastructure & Ops, Code & DevTools · 3 skills · OAuth 2.0

Daytona

API · CLI

Secure compute platform for AI-generated code. Provisions isolated dev environments with git integration. Built for…

Verifiedby Daytona · Browser & Computer Use · 5 skills · API Key

Maki

CLI

Rust coding agent CLI with tree-sitter code indexing, sandboxed Python execution, and multi-tier subagents. Benchmarks…

Verifiedby Maki · Code & DevTools · 3 skills · API Key

SandBase Harness

CLI · MCP

Runs local-first, self-hosted AI agents with persistent sessions, sandboxed tools, memory, credentials, audit trails…

Verifiedby SandBaseAI · Orchestration, Code & DevTools · 3 skills · No auth

Amazon Bedrock AgentCore

API · MCP · CLI

Production agent runtime on AWS with microVM isolation, 8-hour sessions, persistent memory, browser automation, MCP…

VerifiedOfficialby Amazon Web Services · Infrastructure & Ops · 3 skills · API Key

Hronaut

MCP

Provides coding agents a visible local Electron browser through MCP, with persistent isolated workspaces and human…

Verifiedby Hronom · Browser & Computer Use, Code & DevTools · 3 skills · No auth

Vercel Agent Harnesses

API

Runs Claude Code, Codex, OpenCode, and Pi as durable harnesses whose turns resume after crashes or timeouts, for teams…

VerifiedOfficialby Vercel · Orchestration, Code & DevTools · 4 skills · Bearer Token

Modal

API · CLI

Serverless cloud for running Python functions, GPU workloads, and sandboxed agent code, defined in code and deployed…

VerifiedOfficialby Modal · Infrastructure & Ops · API Key

Gemini CLI

CLI · MCP

Google's open-source AI agent CLI that brings Gemini into your terminal with MCP client support, tool use, code…

VerifiedOfficialby Google · Code & DevTools · 3 skills · OAuth 2.0

Pydantic AI

CLI · MCP

Type-safe Python agent framework from the Pydantic team. Built-in MCP client, ships a sandboxed Python execution MCP…

Verifiedby Pydantic · Infrastructure & Ops · 3 skills · API Key

Klavis AI

API · MCP · CLI

Connects agents to 100+ third-party MCP integrations with managed OAuth, hosted or self-hosted servers, and Strata…

Verifiedby Klavis AI · Orchestration, Infrastructure & Ops · 5 skills · API Key

Strands Box

CLI

Sandboxes agent programs with OS-level file, program, and network limits plus Dogwood policy rules enforced across…

VerifiedOfficialby AWS · Security, Infrastructure & Ops · 5 skills · No auth

Clawk

CLI

Gives coding agents a disposable, network-restricted Linux VM with root in the guest while your files and keychain stay…

Verifiedby Clawkwork · Infrastructure & Ops · 3 skills · No auth

Container Use

MCP · CLI

MCP server that gives coding agents isolated containerised environments in separate git branches, enabling multiple…

Verifiedby Dagger · Infrastructure & Ops · 3 skills · No auth

ToolHive

CLI · API · MCP

Runs MCP servers in isolated containers locally or on Kubernetes, with a CLI, desktop UI, operator, registry, and…

Verifiedby Stacklok · Infrastructure & Ops, Security · 4 skills · No auth

Cua

API

Open-source infrastructure for computer-use agents — virtualized macOS, Linux, and Windows sandboxes, SDKs, and…

Verifiedby trycua · Browser & Computer Use · 3 skills · API Key

IronClaw

CLI · API

Runs a self-hosted, security-focused personal assistant in Rust with WASM-sandboxed tools, routines, persistent memory…

Verifiedby NEAR AI · Autonomous Agents, Security · 5 skills · API Key

OpenComputer

API · CLI

Deploys TypeScript agents onto real Linux machines with durable sessions and tool support, hosted or self-run.…

Verifiedby Digger · Infrastructure & Ops, Orchestration · 3 skills · API Key

Devin

API · Extension

Autonomously plans, writes, tests, and ships production code end-to-end with its own shell, code editor, and browser in…

VerifiedOfficialby Cognition AI · Code & DevTools, Autonomous Agents · Bearer Token

Notion Workers

API

Hosts custom code Workers in a secure sandbox and connects external AI agents like Claude and Codex into Notion…

VerifiedOfficialby Notion · Infrastructure & Ops · OAuth 2.0

AutoGen

API · CLI

Microsoft's open-source multi-agent framework. Supports conversational, autonomous, and human-in-the-loop agent…

VerifiedOfficialby Microsoft · Infrastructure & Ops, Orchestration · 5 skills · API Key

Hilt Pay Agent Gateway

API · MCP

Gives agents x402 V2 paid-request access on Solana USDC — settlement verification, receipts, entitlements, atomic…

Verifiedby Hilt · Commerce & Payments, Infrastructure & Ops · 4 skills · API Key

Cloudflare Computer

API

Gives agents on Cloudflare Workers a durable SQLite-backed filesystem in a Durable Object, with shell, JavaScript, and…

VerifiedOfficialby Cloudflare · Infrastructure & Ops, Code & DevTools · 5 skills · No auth

machine0

API · CLI

Persistent CPU and GPU virtual machines for agents that need long-running state, letting a session keep its filesystem…

Verifiedby machine0 · Infrastructure & Ops · API Key

Sprites (Fly.io)

CLI · API · MCP

Gives agents persistent Linux computers with checkpoint and restore, per-Sprite HTTPS URLs, and credential-free…

Verifiedby Fly.io · Browser & Computer Use, Infrastructure & Ops · 5 skills · Bearer Token
/browse
43 agents fit the task · task: run-code-in-a-sandbox
official: 20 · verified: 43 · no-auth: 14 · api: 32 · mcp: 15 · cli: 34 · browser-extension: 1
I need to run code in a sandbox: Run code an agent writes in an isolated container or microVM, away from your machine. Picked from listings that mention sandbox, code execution, isolated or microvm in their name, description, tags or skills; those in Infrastructure & Ops or Code & DevTools, or with API access, rank higher. Best fits with why: /tasks/run-code-in-a-sandbox · without the task: /browse
results
vercel-sandboxbrowser-computerapi+clicube-sandboxinfrastructureapiperplexity-spaceinfrastructureapi+clisandbox0infrastructureapi+cliopensandboxinfrastructureapi+mcp+clidocker-sandboxesinfrastructureapi+cliagent-substrateinfrastructureapi+cliboxliteinfrastructureapi+clidigitalocean-managed-agentsinfrastructureapi+cli+mcpnvidia-openshellsecuritycli+apicodex-clicode-devtoolscli+mcpmicrosoft-mxcsecurityapi+clicontext-modecode-devtoolsmcp+clideepseek-harnessorchestrationcli+apiopenhandscode-devtoolsapi+clie2bbrowser-computerapi+cligoogle-axorchestrationapi+cliopenai-agents-apiorchestrationapi+mcppi-podinfrastructureclidaytonabrowser-computerapi+climakicode-devtoolsclisandbase-harnessorchestrationcli+mcpbedrock-agentcoreinfrastructureapi+mcp+clihronautbrowser-computermcpvercel-agent-harnessesorchestrationapimodalinfrastructureapi+cligemini-clicode-devtoolscli+mcppydantic-aiinfrastructurecli+mcpklavisorchestrationapi+mcp+clistrands-boxsecuritycliclawkinfrastructureclicontainer-useinfrastructuremcp+clitoolhiveinfrastructurecli+api+mcpcuabrowser-computerapiironclawautonomous-agentscli+apiopencomputerinfrastructureapi+clidevincode-devtoolsapi+browser-extensionnotion-workersinfrastructureapiautogeninfrastructureapi+clihilt-paycommerce-paymentsapi+mcpcloudflare-computerinfrastructureapimachine0infrastructureapi+clifly-spritesbrowser-computercli+api+mcp