by eugene1g · Agent Tool · ★ 1.8k
Agent Safehouse Sandbox your LLM coding agents on macOS so they can only access the files and integrations they actually need. Agent Safehouse uses with composable policy profiles and a deny-first model. It supports major coding agents and app-hosted agent workflows while keeping normal development usage practical. Philosophy Agent Safehouse is designed around practical least privilege: Start from deny-all. Allow only what the agent needs to do useful work. Keep developer workflows productive. Make risk reduction easy by default.
| Stars | 1,782 |
| Forks | 68 |
| Language | Shell |
| Category | Agent Tool |
| License | Apache-2.0 |
| Quality Score | 47.42/100 |
| Open Issues | 20 |
| Last Updated | 2026-05-20 |
| Created | 2026-02-09 |
| Platforms | claude-code, cli |
| Est. Tokens | ~62k |
Explore other popular agent tool tools:
agent-safehouse is Sandbox your local AI agents so they can read/write only what they need. It is categorized as a Agent Tool with 1.8k GitHub stars.
agent-safehouse is primarily written in Shell. It covers topics such as ai-agents, claude-code, llm.
You can find installation instructions and usage details in the agent-safehouse GitHub repository at github.com/eugene1g/agent-safehouse. The project has 1.8k stars and 68 forks, indicating an active community.
agent-safehouse is released under the Apache-2.0 license, making it free to use and modify according to the license terms.