I need to run code in a sandbox
Run code an agent writes in an isolated container or microVM, away from your machine.
43 tools · 20 official
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

Vercel Sandbox
API · CLIRuns untrusted or agent-generated code in isolated Firecracker microVMs on Vercel, with snapshots, persistent…
VerifiedOfficialby Vercel · Browser & Computer Use, Infrastructure & Ops · 5 skills · Bearer TokenWhy Isolated MicroVMs: Runs each sandbox in a Firecracker microVM with its own filesystem and network.

CubeSandbox
APIRuns 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 authWhy Snapshot Clone Rollback: Checkpoints running sandboxes with the CubeCoW copy-on-write engine, then rolls back to or forks from any saved state.

Perplexity SPACE
API · CLIRuns 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 TokenWhy Sandbox Lifecycle: Creates sandboxes from templates and pauses, suspends, wakes or deletes them through asynchronous operations you poll.

Sandbox0
API · CLIRuns 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 KeyWhy Create Sandbox: Provisions an isolated cloud sandbox for running untrusted or agent-generated code via the REST API or CLI.

OpenSandbox
API · MCP · CLIRuns AI-agent workloads in isolated Docker or Kubernetes sandboxes, exposing sandbox lifecycle, command, filesystem…
Verifiedby OpenSandbox Group · Infrastructure & Ops, Code & DevTools · 5 skills · API KeyWhy Sandbox Lifecycle Management: Creates, times out, and kills container sandboxes from a chosen image through one lifecycle API on Docker or Kubernetes.

Docker Sandboxes
API · CLIDisposable, isolated container sandboxes for running untrusted agent-generated code, with filesystem and network…
VerifiedOfficialby Docker · Infrastructure & Ops, Security · API Key
Agent Substrate
API · CLIRuns 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 authWhy Sandbox Execution: Runs untrusted agent-generated code inside an isolated microVM with a strict syscall boundary.

BoxLite
API · CLIEmbeds 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 authWhy Isolated Code Execution: Runs commands in a per-box hardware-virtualized VM with streamed stdout and stderr, PTY support, and timeouts.

DigitalOcean Managed Agents
API · CLI · MCPRuns agent harnesses like Claude Code, Codex CLI, and LangGraph in isolated cloud microVM sessions, with governed…
VerifiedOfficialby DigitalOcean · Infrastructure & Ops, Orchestration · 4 skills · Bearer TokenWhy Session Lifecycle: Launches, attaches, pauses, resumes, and removes isolated microVM agent sessions with doctl harness-runtime, keeping state across…

NVIDIA OpenShell
CLI · APIRuns autonomous agents in isolated sandboxes with kernel-level policy enforcement over files, syscalls, and network…
VerifiedOfficialby NVIDIA · Security, Infrastructure & Ops · 4 skills · No authWhy Agent Sandboxes: Creates and manages isolated agent sandboxes from the openshell CLI, with configurable images, runtimes, GPU access, and lifecycle.

Codex CLI
CLI · MCPRuns 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 2.0Why Sandboxed Code Execution: Edits files and runs shell commands inside an OS-level sandbox, escalating to the user for approval per the configured…

Microsoft Execution Containers (MXC)
API · CLIRuns 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 authWhy Policy-Driven Sandboxing: Applies JSON filesystem, network, and UI policies to each contained workload.
Official
The ones published by the company behind the product.
Vercel Sandbox
CubeSandbox
Perplexity SPACE
Docker Sandboxes
DigitalOcean Managed Agents
NVIDIA OpenShell
Codex CLI
Microsoft Execution Containers (MXC)
Related tasks
- monitor apps in production44 tools





Query logs, errors, metrics and incidents from your monitoring tools. - deploy and host an app52 tools





Deploy and host apps, APIs, models and MCP servers from an agent or the command line. - write and fix code34 tools





Coding agents and AI editors that write, edit and debug code in your terminal, editor or browser. - query a database46 tools





Ask Postgres, MySQL, MongoDB and other databases questions, run SQL and manage schemas from an agent.
In stacks
Missing a tool that does this? Suggest a listing.