Microsandbox

Docker Sandboxes is a Docker-developed proprietary tool for running AI coding agents and other workloads inside isolated microVMs on a local machine or Docker-managed cloud infrastructure. Each sandbox has its own kernel and filesystem, controls access to the host filesystem, network, and tools, provides a private Docker daemon for test containers, uses secret placeholders, blocks network access by default, and records an audit trail. It supports agents including Claude Code, Codex, Gemini CLI, and OpenCode, with configurable network and filesystem rules, read-only mounts, MCP catalogs, and policy-based governance controls. It is distributed as the `sbx` command-line tool for macOS, Windows, and Linux, with stable, release-candidate, and nightly builds.

Kubernetes-sigs Agent Sandbox creates isolated, disposable environments for running untrusted or agent-generated code. It is intended to separate such code execution from other workloads.

OpenShell is an open-source runtime from NVIDIA and a structural safety safeguard for running fleets of autonomous AI agents in isolated sandboxes, complementing model-based policy checks. It lets agents read files, install packages, call APIs, and use credentials while enforcing declared filesystem, process, and network policies. Each agent runs in a sandbox where kernel-level controls govern file access, system calls, and network connections. OpenShell also uses formal verification to review policy changes before approval, flagging newly permitted access such as connections to additional hosts with credentials or calls to new API methods. Credentials are withheld from agents and added only to requests bound for approved endpoints. The project provides a CLI, local gateway, sandbox lifecycle management, policy tooling, inference-provider routing, Kubernetes deployment, extensibility APIs, and Python, TypeScript, Go, and Rust SDKs.

Apache Maka (Incubating) is a local-first agent workspace developed under the Apache Software Foundation. It inspects projects and runs tools through a shared Runtime Host within a sandbox boundary; tools that leave the sandbox require approval. Model messages, tool calls, tool results, and how a turn ended are stored as recoverable execution facts on the user's machine, while older tool output can be omitted from later prompts without deleting the saved history. Model connections can use cloud APIs, local models, or compatible gateways, with sessions, settings, and run records kept local by default. Maka provides an Electron and React desktop application with streaming sessions, tool timelines, branching, search, recovery, artifacts, and model and sandbox settings. Its TUI/CLI supports work in a project directory and non-interactive turns, while its evaluation surface runs declarative multi-arm experiments across Maka and external subjects. Built-in tools include Read, Write, Edit, Bash, Glob, and Grep; Computer Use and catalog skills are optional. The project is under active development and Apache incubation; the README describes the macOS Apple Silicon desktop build as an early public release and notes that data formats, CLI commands, and experimental capabilities may change.