Agent Sandboxesagentsandboxes.org
Sandbox profile · Local / OS-level

Agent Safehouse

Answer in brief

Apache-2.0 Bash script that runs Claude Code, Codex and other coding agents under a deny-first macOS sandbox-exec policy, granting the project directory and denying SSH keys, credentials and other repos. A zero-dependency, deny-first sandbox-exec wrapper for local coding agents on macOS; it reduces blast radius rather than providing VM-grade isolation.

By the Agent Sandboxes editors · Updated

Overview

Agent Safehouse "sandboxes LLM coding agents on macOS so they can only access paths they need". It is a single self-contained shell script (also installable with Homebrew) that assembles composable sandbox-exec profiles into a deny-first policy and runs the agent inside it, for example safehouse claude --dangerously-skip-permissions. The site lists Claude Code, Codex, OpenCode, Amp, Copilot CLI, Gemini CLI, Aider, Goose, Cursor Agent, Cline and others, with per-agent investigation pages in the docs.

By default the selected invocation directory is read/write (Safehouse "does NOT auto-widen the default workdir to an enclosing Git repo"), system and toolchain paths are readable, and SSH private keys, shell startup files, browser profile data, the clipboard and cloud credential stores are denied unless opted in with --enable flags. Environment variables are sanitized and network access is open. The project calls itself "a hardening layer, not a perfect security boundary" and recommends running it inside a VM when stronger isolation is needed. macOS only; the latest GitHub release is v0.13.1 (November 2026).

Notable

  • Single self-contained Bash script; no dependencies beyond Bash and macOS
  • Deny-first: SSH keys, other repos, browser data and cloud credentials denied unless explicitly enabled
  • README: "a hardening layer, not a perfect security boundary against a determined attacker"

Agent Safehouse specifications

AttributeDetails
IsolationmacOS Seatbelt via sandbox-exec: composable policy profiles assembled into a deny-first policy around the agent process on the host kernel; the docs describe it as "a host-level macOS policy wrapper, not a VM boundary"
DeploymentLocal / OS-level
Open sourceYes (Apache-2.0)
SDKs and interfacesCLI
Cold start (vendor claim)Not documented
Max session lengthNot documented
PersistenceWorks directly on the host filesystem: the selected workdir (the invocation directory by default, or --workdir) is read/write, extra paths can be granted read/write or read-only, and installed toolchains are readable
GPUNot documented
NetworkingNetwork access is open by default "for registries, APIs, remotes, and MCP servers"; the docs list data exfiltration over the network from readable files among what Safehouse does not fully protect against
PricingFree (Apache-2.0)
Free tierFree
ComplianceNot documented
RegionsNot documented
Company headquartersNot documented

Facts from Agent Safehouse’s public documentation, verified November 18, 2026. Performance numbers are vendor claims.

Strengths and trade-offs

Strengths

  • You run coding agents in permissive or yolo modes on a Mac and want the blast radius limited to the project
  • You want native toolchains to keep working with no VM, container or workspace sync
  • You want per-feature opt-ins (Docker, Keychain, clipboard, Xcode) instead of all-or-nothing access

Trade-offs

  • macOS only
  • OS-level policy on the host kernel; the docs state it is not a VM or hypervisor boundary
  • Network is open by default and egress filtering is not documented

Good fit for: Confining local coding agents on a Mac to the project directory with near-zero overhead and no VM or container.

How Agent Safehouse compares

SandboxCompany HQIsolationOpen sourceSelf-host / BYOCCold start (vendor)Max sessionSnapshots / pauseGPUSDKs
Agent SafehouseNot documentedsandbox-exec (Seatbelt)YesNo / NoNot documentedNot documentedNot documented / Not documentedNot documentedCLI
Container UseNot documentedDagger containerYesNo / NoNot documentedNot documentedYes / Not documentedNot documentedCLI, MCP server
nonoNot documentedLandlock / SeatbeltYesNo / NoNot documentedNot documentedYes / Not documentedNot documentedCLI, Rust, Python, JavaScript/TypeScript, Go
Anthropic Sandbox RuntimeUnited StatesOS-level (Seatbelt / bubblewrap)YesYes / Not documentedProcess startNot documentedNo / NoNot documentedCLI (srt), TypeScript (npm)
Codex CLI sandboxingUnited StatesSeatbelt / bubblewrap / WindowsYesNo / NoNot documentedNot documentedNot documented / Not documentedNot documentedCLI
Gemini CLI sandboxingUnited StatesSeatbelt or containerYesNo / NoNot documentedNot documentedNot documented / Not documentedNot documentedCLI
MinimalNot documentednamespaces or libkrun microVMYesNo / NoNot documentedNot documentedNot documented / Not documentedNot documentedCLI, MCP server

Head-to-head: Agent Safehouse vs Container Use

See all Agent Safehouse alternatives →

Frequently asked questions

What is Agent Safehouse?
Apache-2.0 Bash script that runs Claude Code, Codex and other coding agents under a deny-first macOS sandbox-exec policy, granting the project directory and denying SSH keys, credentials and other repos. A zero-dependency, deny-first sandbox-exec wrapper for local coding agents on macOS; it reduces blast radius rather than providing VM-grade isolation.
How does Agent Safehouse isolate code?
Agent Safehouse documents its isolation as: macOS Seatbelt via sandbox-exec: composable policy profiles assembled into a deny-first policy around the agent process on the host kernel; the docs describe it as "a host-level macOS policy wrapper, not a VM boundary".
Is Agent Safehouse open source?
Yes (Apache-2.0).
How much does Agent Safehouse cost?
Free (Apache-2.0) Check the official pricing page for current rates.
What are the alternatives to Agent Safehouse?

Sources

  1. agent-safehouse.dev
  2. agent-safehouse.dev/docs/
  3. agent-safehouse.dev/docs/overview.html
  4. agent-safehouse.dev/docs/default-assumptions.html
  5. agent-safehouse.dev/docs/options.html
  6. agent-safehouse.dev/docs/isolation-models.html
  7. github.com/eugene1g/agent-safehouse
  8. github.com/eugene1g/agent-safehouse/releases

Check before you rely on it. Products change quickly, and this page reflects public documentation as of November 18, 2026. Confirm anything that matters in the provider’s own documentation.

Cite this page

Agent Sandboxes. (2026). Agent Safehouse. agentsandboxes.org. Last reviewed November 18, 2026. https://agentsandboxes.org/sandboxes/agent-safehouse/