sandbox

A local zero-dependency sandbox for agents that records files, commands, database activity, network access, and screenshots for review before approving changes.

A harness that runs MCP servers in a disposable Linux sandbox and logs their real startup behavior, including file access and outbound network connections.

Bestie is an open-source native terminal coding agent harness focused on visibility and control, with sandboxing, provider support, session save/load, and cross-platform installs.

Code Airlock is a wrapper for running coding agents like Claude Code and Codex inside disposable microVMs, with changes committed to git for host-side review.

A Docker-based sandbox for running AI coding agents with dropped capabilities, no-new-privileges, and no Docker socket access. It wraps the pi terminal coding agent and supports local file edits, persistent auth, and skills mounts.

A Claude Code plugin that wraps MCP tool use in a single sandboxed JavaScript program, reducing tool-call chatter and keeping intermediate results out of context.

A curated dataset of sandboxes and related approaches for running AI coding agents with isolation, network control, or credential mediation.

Autolang is a scripting language and compiler for AI agent code, designed to run untrusted AI-written scripts in a controlled environment with restricted access to registered functions.

An open-source multiplayer agent harness for work, designed for Slack and web-based collaboration with scoped memory, permissions, sandboxes, and admin controls.

A blog post describing ptc_runner’s MCP server and code-mode approach, where agents run short-lived untrusted programs inside a small Lisp REPL instead of Python or JavaScript.