#sandbox

Secure Node.js Execution Without a Sandbox A lightweight library for secure Node.js execution. No containers, no VMs — just npm-compatible sandboxing out of the box.

Terminal-native AI coding agent running in containers.

A faster, lighter, cheaper alternative to sandboxes. Run any coding agent inside an isolated Linux VM, with agent orchestration built in.

A faster, lighter, cheaper alternative to sandboxes. Run any coding agent inside an isolated Linux VM, with agent orchestration built in.

Typescript Workflow builder, optimized for use in Coding Agents

Node.js for inside the browser. An open-source, lightweight WebContainer alternative.

Kubernetes operator for stateful VM-backed pod workflows. Provides Hibernation CRD to suspend and wake VMs without pod deletion, and CocoonSet CRD to manage groups of related VM-backed pods with stable slot identities. Keeps stateful VM workloads inside native Kubernetes APIs.

The runtime substrate for agentic systems — one Go binary, six LLM providers, MCP-native, configurable as a managed sandbox or full agentic dev environment. Where agents live, talk, and learn.

Run multiple agents in parallel sandboxed VMs, with a single command, on your PC or in the cloud

该仓库未发布描述。

Give coding agents a disposable Linux VM, not your laptop

Fast cold-boot MicroVM sandboxes for AI agents on cocoon

Sandbox runtime for AI coding agents. Firecracker microVMs, a single Go binary, snapshot/fork as first-class primitives.

Provides easy-to-use Linux seccomp-bpf jailing.

Sandboxed TypeScript runtime for AI coding agents to query AWS — full SDK access with in-sandbox aggregation, credentials flow via IMDS and never enter the VM. Ships as a Claude Code plugin (MCP) and a standalone CLI, backed by Shuru microVMs or Docker.

该仓库未发布描述。

A bash tool for AI SDK

Reusable detonation framework: run untrusted documents through disposable, hardened workers

Sandboxed JSON-over-stdin/stdout tool executor for AI coding agents with 19 tools, workspace confinement, and guarded mutation.

A sandbox for Elixir to safely evaluate untrusted code from user input

A lightweight, in-process sandbox for safely executing the tool calls an AI agent requests

A Sui-native, policy-bound, non-custodial AI finance agent. Natural-language goals → policy-checked PTBs, executed only within approved on-chain scope, with auditable Walrus receipts.

A pure-Go IL/CIL interpreter for running real C# assemblies and NuGet packages inside a Go program — no .NET runtime installed on the host.

Sandbox any macOS app — only your project directory stays accessible

Run Node.js, Python, Rails, and other full-stack runtimes directly in the browser. A browser-native code sandbox.