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 | 2,050 |
| Forks | 90 |
| Language | Shell |
| Category | AI 工具 |
| License | Apache-2.0 |
| Quality Score | 64.7427036160694/100 |
| Open Issues | 26 |
| Last Updated | 2026-09-07 |
| Created | 2026-02-09 |
| Platforms | claude-code, cli |
| Est. Tokens | ~11k |
Explore other popular ai 工具 tools:
agent-safehouse is Sandbox your local AI agents so they can read/write only what they need. It is categorized as a AI 工具 with 2.0k 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 2.0k stars and 90 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.