Agent Safehouse
by eugene1gSandbox your local AI agents so they can read/write only what they need
Agent Safehouse is an open-source ai agent by eugene1g, written mainly in Shell, with 2,131 GitHub stars and the Apache-2.0 license. Its code was last updated Oct 21, 2026.
Scan summary: scanned Nov 5, 2026 at commit 0812967. No capabilities flagged by our checks. Scan policy
What Agent Safehouse can touch
- Our checks did not find this. The tool may still do it.Run shell commandsNot seen in this scan
- Our checks did not find this. The tool may still do it.Run dynamic codeNot seen in this scan
- Our checks did not find this. The tool may still do it.Read or write filesNot seen in this scan
- Our checks did not find this. The tool may still do it.Read environment and secretsNot seen in this scan
- Our checks did not find this. The tool may still do it.Control a web browserNot seen in this scan
- Our checks did not find this. The tool may still do it.Connect to databasesNot seen in this scan
- Our checks did not find this. The tool may still do it.Read or send messagesNot seen in this scan
- Our checks did not find this. The tool may still do it.Touch money or tradingNot seen in this scan
- Our checks did not find this. The tool may still do it.Connect to the internetNot run in this scan
"Not seen" means our checks did not find it, and the tool may still do it. Covers commit 0812967, Nov 5, 2026. See the scan policy.
Before you install Agent Safehouse
AgenticMart scanned Agent Safehouse on Nov 5, 2026 with automated checks for hidden code, known-malicious packages, leaked secrets and vulnerable dependencies. The result covers one commit under our scan policy, so review what access you give it and check any advisories shown here.
What it can access
- An AI agent decides its own next steps and calls whatever tools you give it, so its risk depends on the access you grant.
Before you install
- Pin the version you reviewed instead of always installing the latest release.
- Read the tool list or scripts before the first run, and keep approval prompts on for actions that write, send or delete.
- Maintained by eugene1g on GitHub, 2,131 stars and 99 forks. Popularity is not proof of safety.
- Last code change: Oct 21, 2026.
- Open-source license: Apache-2.0.
Agent Safehouse is an open-source ai agent by eugene1g, written mainly in Shell. Sandbox your local AI agents so they can read/write only what they need
At a glance
- Stars
- 2.1k
- Forks
- 99
- Language
- Shell
- License
- Apache-2.0
- Created
- Feb 2026
- Last update
- Oct 21, 2026
- Type
- AI Agent
- Price
- Free
Topics
Questions about Agent Safehouse
What is Agent Safehouse?
Sandbox your local AI agents so they can read/write only what they need
Who maintains Agent Safehouse?
Agent Safehouse is maintained by eugene1g on GitHub (eugene1g/agent-safehouse). AgenticMart lists it from public repository data.
Is Agent Safehouse safe to use?
AgenticMart scanned Agent Safehouse on Nov 5, 2026 with automated checks for hidden code, known-malicious packages, leaked secrets and vulnerable dependencies. The result covers one commit under our scan policy, so review what access you give it and check any advisories shown here.
What license does Agent Safehouse use?
It is published under the Apache-2.0 license.
Agent Safehouse alternatives
View more →Similar ai agents in Security & Testing, ranked by GitHub stars. Compare licence, recent activity and scan status before you choose.
| Name | Stars | Licence | Last updated | Scan |
|---|---|---|---|---|
| Agent Safehouse (this page) eugene1g | 2.1k | Apache-2.0 | Oct 21, 2026 | Scanned, no flagged issues |
| ECC affaan-m | 294k | MIT | Oct 30, 2026 | Scanned, no flagged issues |
| Strix usestrix | 73k | Apache-2.0 | Oct 30, 2026 | Scanned, no flagged issues |
| Goose aaif-goose | 56k | Apache-2.0 | Nov 1, 2026 | Scanned, no flagged issues |
| Anthropic Cybersecurity Skills mukul975 | 35k | Apache-2.0 | Aug 31, 2026 | Scanned, no flagged issues |
| Pentagi vxcontrol | 33k | MIT | Oct 22, 2026 | Scanned, no flagged issues |