GreyhavenHQ/greywall
CLI agent sandbox with with dynamic config & visibility via greyproxy.
This tool helps developers safely experiment with AI coding agents like Claude Code or Cursor. It creates a secure, isolated environment where you can run these agents without fear of them accessing sensitive files, credentials, or making unwanted network connections. You input your AI agent or command, and it ensures it only operates within permitted boundaries, providing peace of mind during AI-assisted development.
Use this if you are a software developer who wants to leverage AI coding assistants securely, preventing them from inadvertently accessing or modifying sensitive parts of your system.
Not ideal if you need to run AI agents that require broad, unrestricted access to your entire system or specific network resources outside of a controlled environment.
Stars
45
Forks
10
Language
Go
License
Apache-2.0
Category
Last pushed
Mar 13, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/GreyhavenHQ/greywall"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
looplj/axonhub
⚡️ Open-source AI Gateway — Use any SDK to call 100+ LLMs. Built-in failover, load balancing,...
generalaction/emdash
Emdash is the Open-Source Agentic Development Environment (🧡 YC W26). Run multiple coding agents...
vercel-labs/opensrc
Fetch source code for npm packages to give AI coding agents deeper context
andyvandaric/opencode-ag-auth
Enhanced Antigravity OAuth plugin for OpenCode strict quota locking, multi-account rotation,...
alchemiststudiosDOTai/tunacode
🍣 TunaCode AI CLI coding agent with safe git branches, rich tools & multi-LLM support.