sandvault

Name: sandvault
Author: webcoyote

webcoyote September 12, 2025

217 copies 0 downloads

Run AI agents isolated in a macOS user account and sandbox-exec. Configured to run Claude Code, OpenAI Codex, Cursor Agent, Google Gemini.

SandVault - Run AI agents and shell commands in a sandboxed macOS user account

<img src="https://www.codeofhonor.com/images/projects/sandvault.webp" align="left" width="200px"/> SandVault (`sv`) manages a limited user account to sandbox shell commands and AI agents, providing a lightweight alternative to application isolation using virtual machines. </br> </br>

AI ready - Includes Claude Code, OpenAI Codex, OpenCode, Google Cursor
Fast context switching - No VM overhead; instant user switching
Passwordless - switch accounts without a prompt (after setup)
Shared workspace - joint access to /Users/Shared/sv-$USER
Defense in depth - limited user account + sandbox-exec
Clean uninstall - Complete removal with sv uninstall

</br> </br>

Quick Links

Run Browser Automation from within the sandbox that can be used for testing web interactions.
To run xcodebuild or swift see Sandboxing xcodebuild and swift for details.
To run other sandboxed applications inside sandvault, use the -x option. See Sandboxing other apps for details.
It's not possible to run GUI applications from within the sandbox; see Running GUI Applications for details.

Security Model

SandVault has limited access to your computer:

Cannot access your home directory
Runs with standard user privileges
Cannot modify system files
Has no access to mounted drives

- writable:  /Users/Shared/sv-$USER         -- only accessible by you & sandvault-$USER
- writable:  /Users/sandvault-$USER         -- sandvault's home directory
- readable:  /usr, /bin, /etc, /opt         -- system directories
- no access: /Users/*                       -- other user directories

- writable:  /Volumes/Macintosh HD          -- accessible as per file permissions
- no access: /Volumes/*                     -- cannot access mounted/remote/n

Comments

More Agents

View all

agent-memory

Emulo

Mine your Claude Code and Codex logs into a local you.md agent profile.

ohad6k

193

lm-studio

Nyx Local Ai

Local-first AI coding agent for VS Code & Cursor. Ollama, LM Studio & your inference fleet. Cursor-grade agent UX — offline, private, zero token cost.

sthamann

248

Self Learning Skills

A self-improving skill for AI coding agents (Claude Code, Cursor, AGENTS.md): recognize a hard-won golden path in a session and harvest it into a reusable skill/rule for next time.

Kulaxyz

895

agentic-ai

FDEOps

Second brain for Forward Deployed Engineers. Engagement memory + 35 skills across 6 domains, all behind one @fde... Works with any AI coding agent.

suboss87

303

agent-skills

Awesome Gamedev Agent Skills

Game-development Agent Skills for AI coding agents: install once and a master router loads the right skill for your engine and task. 66 original, version-pinned skills (plus a master router) in the portable SKILL.md format that runs across Claude Code, Cursor, Codex, Copilot, Gemini CLI and more, for Godot, Unity, Unreal, web and beyond.

gamedev-skills

301

agents

Honey For Devs

Honey (I Shrunk the AI) by GreenPT: a cross-tool coding skill that cuts AI coding-agent token usage and LLM API costs — write less code, less prose, and denser agent-to-agent handoffs (−53%, lossless in benchmarks) with no loss of quality. Works with Claude Code, Cursor, GitHub Copilot, Codex, Gemini CLI, Windsurf, Cline & Kiro.

Green-PT

177