instavm/coderunner
A local sandbox for your AI agents
This tool creates a secure, isolated environment on your Mac where you can safely run code from various AI agents like Claude, OpenAI, or Gemini. It takes your AI's code execution requests and runs them in a protected sandbox, preventing any unintended access to your personal files or system. This is designed for AI developers and researchers who need to test AI agent code without risking data loss or system compromise.
801 stars. Actively maintained with 3 commits in the last 30 days.
Use this if you are developing or experimenting with AI agents that generate and execute code, and you need a secure, local sandbox to prevent potential data breaches or system damage.
Not ideal if you are a casual user of AI tools and do not need to execute arbitrary code or develop AI agents.
Stars
801
Forks
36
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 11, 2026
Commits (30d)
3
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/instavm/coderunner"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related agents
hesreallyhim/awesome-claude-code
A curated list of awesome skills, hooks, slash-commands, agent orchestrators, applications, and...
bfly123/claude_code_bridge
Real-time multi-AI collaboration: Claude, Codex & Gemini with persistent context, minimal token overhead
fengshao1227/ccg-workflow
多模型协作开发系统 - Claude 编排 + Codex 后端 + Gemini 前端，28 个命令覆盖开发全流程，一键安装零配置
njbrake/agent-of-empires
Claude Code, OpenCode, Mistral Vibe, Codex CLI, Gemini CLI, Pi.dev, Copilot CLI Coding Agent...
harikrishna8121999/antigravity-workflows
Community-driven workflows for Antigravity AI. Like Claude Skills - reusable prompts and...