Agent Safehouse
macOS sandbox for local coding agents that limits file and integration access with deny-first policy profiles.
Updated
✨ Try AgentScout's free AI image generator →Good for: writing code, running code safely, agent security and safety
Use cases
About Agent Safehouse
Agent Safehouse is listed in our sandboxes & code execution category and is aimed at builders. macOS sandbox for local coding agents that limits file and integration access with deny-first policy profiles. Pricing, as the maker states it: Open source. Maturity: Active. We last checked the official link on 2026-10-18.
Agent Safehouse at a glance
- Category: Sandboxes & code execution
- Built for: Developers and teams building with AI agents
- Pricing: Open source (as the maker states it)
- Licence: Apache License 2.0 (OSI-approved open source)
- GitHub: eugene1g/agent-safehouse · 2,117 stars (as of Oct 21, 2026)
- Latest release: v0.12.0, Sep 7, 2026
- Last commit: Oct 19, 2026
- Official site: agent-safehouse.dev
- Listed on AgentScout: Oct 18, 2026
Agent Safehouse FAQ
What is Agent Safehouse?
macOS sandbox for local coding agents that limits file and integration access with deny-first policy profiles.
How much does Agent Safehouse cost?
Agent Safehouse's pricing, as the maker states it: Open source. Open-source tools are free to use, though you may still pay for model API usage or a hosted plan. Check the official site for current plans.
Is Agent Safehouse open source?
Yes. Agent Safehouse's GitHub repository is published under the Apache License 2.0, according to the licence file in the repo.
Where can I find Agent Safehouse's source code?
On GitHub at eugene1g/agent-safehouse, which had 2,117 stars as of Oct 21, 2026. The latest release is v0.12.0 (Sep 7, 2026).
What are alternatives to Agent Safehouse?
Similar tools include OpenSandbox, CubeSandbox, AIO Sandbox, Sandbox0, AgentBay and Perplexity SPACE.
Facts from our link-checked listing, the GitHub repository and the official site. See something wrong? Suggest an edit.
Agent Safehouse ratings and reviews
Be the first to rate Agent Safehouse: tap 1 to 5 stars below. A written review is optional.
Agent Safehouse alternatives
Other sandboxes & code execution tools in our directory. See all sandboxes & code execution tools →
OpenSandbox
Secure, fast sandbox runtime for AI agents to run code.
CubeSandbox
Lightweight, concurrent sandbox for running AI agent code securely.
AIO Sandbox
All-in-one Docker sandbox for AI agents that combines a browser, shell, files, MCP, VS Code Server and Jupyter in one container.
Sandbox0
Sandbox0 is a managed sandbox runtime that gives each AI agent an isolated cloud computer where it can run code, install software, manage files and control network access. The whole writable root filesystem persists across incremental checkpoints and grows automatically as it fills, so an agent can pause compute between tasks and resume the same sandbox later with its tools, dependencies and files intact. It adds snapshots and restore, SSH, egress proxy and credential injection, private previews, Docker in the sandbox, webhooks, warm pools and custom templates, with integrations for LangChain Deep Agents, OpenAI Agents, Vercel and GitHub CI. Sandboxes run under gVisor isolation with Nomad scheduling.
AgentBay
Alibaba Cloud's cloud sandbox service for agents, offering ready-made browser, Linux and Windows desktop, mobile and code environments that agents control through an SDK or MCP.
Perplexity SPACE
Perplexity's open-source sandbox platform that runs each agent task in its own Firecracker microVM, with credentials and network access controlled from outside.
Popular searches with this tool
🧭 Task guides: Guardrail and policy tools for agent security · Sandboxes and secure execution tools for coding agents
Badge for makers
Built Agent Safehouse? Add this badge to your README or site. It links back to this page. About badges