Code & AI agent sandboxes: read the guide

Agent Safehouse

Open source toolSandbox

macOS-native sandboxing for local agents. Move fast, break nothing.

Homepage Docs Repository

Scanned 12 Oct 2026 · Schema v5 · features v21

Licence: Apache-2.0
Self-hosted; you pay for the infrastructure.
Free tier: Free to run
Isolation: Not disclosed
the public docs do not say
Regions: —
Not disclosed on the public surface.
Capabilities: 3 / 61
5 partial · 36 fail · 0 not assessed
Agent readiness: 5/10 · 2/4
read · drive, pre-login surface

Advertised for

Native macOS coding agent CLI sessions · Native desktop/app hosted agents · Local builds and developer commands · Local browser workflows with explicit policy grants

Built for

Developers, then technical

· CLI-first Homebrew/script installation and explicit policy profiles.
· Native macOS coding agents and developer toolchains; no managed app deploy workflow.

01 Runtime Each fact carries its source; dots show confidence. Open a row for the evidence.

Isolation & lifecycle

Isolation primitive

Not disclosedthe public docs do not say

Persistence

Allowed host filesystem files persist; Safehouse does not allocate an isolated disk.

Snapshots / forks

Resources & limits

Storage

Native selected workdir and explicit read/write or read-only host path grants; default workdir is the exact invocation directory in current main docs.

Limits & quotas

Not documented

GPU

Optional --enable=gpu permits local Metal shader compilation and GPU IOKit access; operator supplies hardware.

Access

Deploy interface

cli

SDK languages

None

Network & secrets

Egress controls

Open inbound/outbound TCP/UDP by default; blocking exfiltration/C2 is explicitly not a goal.

Secrets

Sanitized environment by default; --env=FILE and --env-pass selectively inject credentials into the process. Keychain and cloud credential access opt in.

Bring your own cloud

Placement & use

Jurisdiction

Advertised workloads

Native macOS coding agent CLI sessionsNative desktop/app hosted agentsLocal builds and developer commandsLocal browser workflows with explicit policy grants

02 Capabilities 3 pass · 5 partial · 36 fail · 61 of 61 assessed

Supported — Documented on the public surface and verified.
Partially supported — Exists with caveats: gated, thin, or enterprise-only.
Not supported — Checked and not offered.
Not assessed — Scanned before this capability was tracked. Not a lack.

Compute & storage 1/7

Persistent diskStorage that survives restart/stop (not ephemeral-only).

Supported

Object storageManaged S3-compatible / blob object store the platform PROVIDES to a user's workloads (buckets, presigned URLs). DISTINCT from persistent-disk (block/volume attached to an instance) and from a self-host dependency (source.self_host.deps[]=["object-storage"] is an infra dep to RUN an OSS tool — the opposite direction). SCOPE varies and matters: native first-class (Railway Buckets, Cloudflare R2) vs a sibling SKU / extension (Fly Tigris, Bunny Storage, DigitalOcean Spaces) — record which in the evidence quote / note. Admitted v15.

Not supported

Snapshots / forkingSnapshot or copy-on-write fork of a running instance (filesystem-only counts). Whether the snapshot also restores memory + running processes is recorded separately by memory-snapshot (v19).

Not supported

Live-state (memory) snapshotsA snapshot / checkpoint / pause captures a running instance's MEMORY and PROCESS state and restores it, so running processes continue where they left off instead of a freshly booted instance with the same files. Counts whether user-triggered (snapshot, checkpoint, pause-to-storage) or used to restore pre-initialised state (memory snapshots for fast cold starts). Distinct from snapshots-forks (any snapshot or fork, including filesystem-only; a product passing that key may still fail this one) and from scale-to-zero (an idle-cost property; suspension may or may not keep memory). Actor multiplexing (see scale-to-zero) records its live-state half here — only when the suspended actor's MEMORY/process state is what comes back, not a freshly booted worker with the actor's files.

Not supported

Scale to zeroIdle instances suspend at no / negligible cost. ACTOR MULTIPLEXING (many suspended stateful actors sharing a small pool of pre-warmed workers, woken on request — Agent Substrate, AX, kagent; Rivet's hibernating actors) has NO key of its own (proposal REJECTED v20) — score the idle-cost half HERE and the live-state half under memory-snapshot; the oversubscription ratio / density is a performance characteristic the registry does not key.

Not supported

GPU computeGPU-backed instances available.

Partially supported

Multi-regionCompute placeable in more than one geographic region.

Not applicable

Sandbox templates / custom imagesBuild reusable sandbox/VM images from an OCI image or Dockerfile (a base you fork instances from).

Not applicable

Cloud-init / ignition configCustomise a VM / microVM / instance at boot via cloud-init (or ignition) user-data — the same boot-metadata interface as AWS/Azure/GCP. Inject packages, users, SSH keys, files, and run-commands declaratively at launch. Distinct from sandbox-templates (a PREBUILT image you fork instances from) — this is PER-LAUNCH declarative customisation, not a baked image.

Not applicable

Desktop / computer-use sandboxA virtual desktop (GUI) for LLM computer-use — browser + desktop automation, often via noVNC/VNC.

Not applicable

Selectable isolation runtimeThe user chooses the isolation runtime per workload / environment / sandbox from more than one option (e.g. microVM vs gVisor vs plain container, native namespaces vs gVisor, gVisor vs VM). Records the CHOICE; the isolation_primitive facet still records the best-evidenced primary. A platform that switches runtime automatically without a user choice (e.g. gVisor forced for GPU) does not pass on that alone.

Not supported

Networking & delivery 0/7

Automatic HTTPSTLS endpoints provisioned automatically per workload.

Not supported

Built-in reverse proxyPlatform routes external traffic to workload services.

Not supported

Custom domainsBring-your-own domain via CNAME/DNS.

Not supported

Public preview URLsShareable per-deploy / per-branch URLs.

Not supported

Direct public IPv6Per-instance stable public IPv6 for raw TCP/UDP (beyond a managed HTTPS proxy) — e.g. mosh / raw sockets.

Not applicable

Egress controlsConfigurable OUTBOUND network policy — egress firewall / allowlist / egress proxy on traffic LEAVING a workload. Scoped to OUTBOUND only (v15): private-network REACHABILITY between a user's own services is private-networking, not this. Static-egress-IP belongs here (an outbound concept).

Not supported

Private networkingA platform-internal private network between a user's OWN services — service-to-service connectivity, VPC, service mesh, and/or service discovery, not exposed to the public internet. DISTINCT from egress-controls (OUTBOUND firewall/allowlist), reverse-proxy (PUBLIC inbound ingress), and direct-ipv6 (per-instance PUBLIC addressing). Admitted v15.

Not supported

Email send / receiveSend and/or receive email from the workload.

Not supported

Edge KV storeA globally-replicated key-value store read from WITHIN an edge runtime at the PoP (low-latency, eventually-consistent) — Cloudflare Workers KV, Deno KV, Fastly KV Store, Akamai EdgeKV, Vercel Edge Config. Distinct from first-party-db (a managed DATABASE service you provision and connect to) and from http-query-api (HTTP access to an external store) — edge-kv is colocated with the edge compute and read at the edge.

Not applicable

Developer access 1/6

Public APIDocumented programmatic API.

Not supported

OpenAPI specMachine-readable OpenAPI / Swagger spec published.

Not supported

CLIOfficial command-line tool.

Supported

SDKOfficial client library/libraries.

Not supported

SSH accessDirect SSH into workloads.

Not applicable

Filesystem APIRemote file operations over the API (list/read/write/watch/copy/upload) without SSH.

Not supported

Git deployDeploy from a Git repo / push-to-deploy.

Not supported

Private container registryHosted private image registry.

Not applicable

E2B-compatible APIDrop-in compatibility with the E2B sandbox API/SDKs — existing E2B client code runs against this product by changing the endpoint/domain + key, with no business-code changes. E2B itself passes as the reference implementation. Distinct from public-api / sdk (the product has its own API — this key says it also speaks another vendor's) and from self-host-oss (a self-hosted E2B-compatible server is scored on both).

Not applicable

HTTP data APIQuery / read / write the stored DATA over plain HTTP/REST (or GraphQL) WITHOUT the native protocol driver (Postgres wire / Redis RESP) — agent- and edge-friendly data access via fetch(). The DATA plane; distinct from public-api (a control-plane / management API). Auto-generated-from-schema REST/GraphQL (PostgREST, pg_graphql) is a flavour of this.

Not applicable

AI & agents 0/11

Built-in coding agentShips a first-party AI coding agent in the product.

Not supported

Agent skillsInstallable / declarable agent skills or tools.

Not supported

AI app builderPrompt-to-app / vibe-coding generation surface.

Not supported

MCP serverExposes a Model Context Protocol server for agents.

Not supported

MCP clientActs as an MCP client / consumes MCP tools.

Not supported

MCP-server hostingRun/host MCP servers as a workload on the platform (distinct from exposing a first-party MCP control server — that is mcp-server).

Partially supported

LLM gatewayRoutes LLM API calls through the platform (multi-provider).

Not supported

BYOK for LLMsBring-your-own LLM provider keys.

Partially supported

Model inference API (first-party)A FIRST-PARTY hosted LLM/model inference API — the provider serves its OWN catalogue of (usually open-weight) models behind a (typically OpenAI-compatible) endpoint, billed per token. Distinct from llm-gateway (a multi-PROVIDER proxy/router for YOUR calls to external providers like OpenAI/Anthropic) and from byok-llm (bring your own provider keys) — here the platform IS the inference provider, serving its own models.

Not applicable

Autonomous QA agentA first-party AUTONOMOUS AI agent that QA-TESTS a running app / implementation — exercising it like a real user (clicking through flows, checking behaviour) and reporting bugs/defects (often back to a coding agent, or before a human review). Distinct from built-in-agent (a code-AUTHORING agent — this one VERIFIES the result, it does not write the feature; a product can ship both), from ai-guided-code-review (organises a diff for a HUMAN to review — not an autonomous tester), and from observability (runtime metrics/logs, not active testing).

Not supported

Credential-injection proxyThe platform holds real secrets OUTSIDE the workload and injects them on the wire (an egress / broker proxy swaps a placeholder or phantom token for the real credential on matching outbound requests), so code running in the sandbox — e.g. an untrusted agent — never sees or can exfiltrate the real key. Distinct from secrets-management (storage + injection INTO the workload as env vars/files — the workload holds the secret) and from egress-controls (outbound allow/deny POLICY; a product can have an allowlist without injecting credentials, and vice versa).

Not supported

Preinstalled coding agentThe platform installs and launches a THIRD-PARTY coding agent (a harnesses.yml entry — Claude Code, Codex, OpenCode, Pi ...) inside a workspace/sandbox it provisions, with the agent's auth wired in (your own account or API key), so you start an agent session rather than an empty box. Distinct from built-in-agent (a FIRST-PARTY agent the vendor ships) and from harnesses[] (which records that a harness CAN target the product, not that the product runs it for you).

Not supported

Data 0/1

First-party databasePlatform-provided managed database.

Not supported

Database branchingCopy-on-write branch of a DATABASE (schema + data) as a dev-lifecycle primitive — branch your data like code, usually instant via a metadata operation. Distinct from snapshots-forks (forks a running compute INSTANCE / VM state) and from preview-environments (a full per-PR environment that may USE a DB branch). For a data product a CoW branch maps HERE, not to snapshots-forks.

Not applicable

Vector searchFirst-class storage, indexing, and similarity search of vector embeddings — a native vector type/index or a managed vector DB. The data-layer primitive for RAG / semantic retrieval.

Not applicable

Ephemeral instant DB (no-signup)Provision a working, usable instance via a single command / HTTP call with NO account, signup, or card — typically time-boxed (expires unless claimed). A zero-onboarding path an agent can hit directly.

Not applicable

Platform & operations 0/5

Scheduled tasksCron / scheduled job primitive.

Not supported

Durable workflowsDurable execution / long-running workflow primitive.

Not supported

Preview environmentsA full EPHEMERAL environment spun up per PR / branch — compute + addons + (often) a DB branch — torn down on merge. More than preview-urls (which is just a shareable URL for one deploy).

Not supported

Built-in observabilityFirst-party metrics / logs / tracing / APM / profiling included in the platform (no third-party stack required to see what a workload is doing).

Partially supported

Managed CI/CD runnersPlatform-hosted, drop-in CI/CD runner VMs (GitHub Actions / GitLab), typically faster and cheaper than the CI vendor's own hosted runners, billed per runner-minute; isolated + ephemeral per job. Distinct from git-deploy (push-to-deploy of an APP) and scheduled-tasks (cron) — this is managed CI COMPUTE you point your existing pipelines at.

Not applicable

Project template marketplaceA marketplace / gallery of prebuilt PROJECT STARTER templates (apps or websites) a user clones or launches a new project from and then customises — the "start from a template" surface of a builder / PaaS. Distinct from sandbox-templates (a COMPUTE base IMAGE you fork runtime INSTANCES from — Dockerfile / OCI), from app-builder (the prompt-to-app GENERATION surface — a product can have both), and from one-click OSS-app catalogues / helm-addon-marketplace (deploy a FINISHED app as-is, not a starter you build on).

Not supported

Organisation & security 1/7

Built-in authPlatform-provided authentication / IAM for workloads.

Not supported

SSO / SAMLEnterprise single sign-on.

Not supported

Secrets managementFirst-class secrets storage / injection.

Partially supported

TeamsMulti-user team accounts.

Not supported

SharingShare a running workload/resource via link (optionally gated).

Not supported

BYOCRuns inside the customer's own cloud account.

Not applicable

Deploy into customers' VPCsA SaaS vendor uses the platform to deploy and operate ITS software inside ITS CUSTOMERS' cloud accounts / VPCs (nested or "customer BYOC"), managed from the vendor's control plane. Distinct from byoc (your own workloads in your own cloud account).

Not applicable

Workload identityThe platform gives each workload its own verifiable identity (OIDC token, SPIFFE SVID, cloud IAM federation) that it exchanges for short-lived credentials, so no long-lived static secret is stored or injected. Distinct from secrets-management (stores / injects static secrets) and credential-injection-proxy (swaps real secrets in on the wire).

Not supported

Self-host / OSS coreOpen-source core that can be self-hosted.

Supported

Proposed, not verified

Capabilities the scan saw but the registry does not track yet. A key is admitted only once two distinct products exhibit it. These are not scored.

Deny-first composable host filesystem policyhost-filesystem-access-policy
“safehouse composes a final sandbox policy from modular profiles, then runs your command under sandbox-exec.” raw.githubusercontent.com

03 Agent readiness Pre-login surface · counts, not a grade

Can an agent read it?

parse-ability · docs, metadata, machine-readable surfaces

5/10

3 full · 2 partial · 50% of applicable checks

llms.txt
Not supported
“https://agent-safehouse.dev/llms.txt and /docs/llms.txt: HTTP 404; llm-instructions.txt is a policy-generation prompt, not an llms.txt index.”
llms-full.txt
Not supported
“https://agent-safehouse.dev/llms-full.txt: HTTP 404.”
robots.txt AI policy
Partially supported
“https://agent-safehouse.dev/robots.txt: content-signal definitions only; no explicit AI user-agent allow/block rules and no Sitemap pointer.”
JSON-LD
Not supported
“https://agent-safehouse.dev/: no application/ld+json script in retained homepage HTML.”
Sitemap
Not supported
“https://agent-safehouse.dev/sitemap.xml: HTTP 404; robots.txt has no alternate Sitemap pointer.”
Meta tags
Supported
“https://agent-safehouse.dev/: descriptive title, description, OG and Twitter metadata in retained HTML.”
Markdown negotiation
Not supported
“https://agent-safehouse.dev/: Accept text/markdown initially returned Cloudflare 403 error 1010; foxcrawl retry served text/html, not negotiated Markdown. /index.md and /docs/getting-started.md returned 404. GitHub raw Markdown docs remain available.”
Content efficiency
Supported
“https://agent-safehouse.dev/: 4373 readable text bytes / 36351 HTML bytes = 12.03%, after excluding scripts/styles.”
Docs discoverable
Supported
“https://agent-safehouse.dev/: server-rendered main navigation links Docs at /docs/.”
Machine-readable pricing
Not applicable
“Self-host-only Apache-2.0 local tool; no hosted pricing tier applies.”
No anti-bot wall
Partially supported
“https://agent-safehouse.dev/: ordinary HTML/docs fetches succeeded; Accept text/markdown got Cloudflare signature-ban 403. Browser retry succeeded with HTTP 200, blocked:false.”

Can an agent drive it?

act-ability · APIs, SDKs, MCP, credentials, webhooks

2/4

1 full · 1 partial · 50% of applicable checks

Public API
Not applicable
“Local command wrapper, no hosted API endpoint.”
OpenAPI spec
Not applicable
“No HTTP API to describe; /openapi.json HTTP 404 and docs/tree contain no linked spec.”
MCP server
Not supported
“/.well-known/mcp HTTP 404; no first-party MCP control server in docs/tree. Wrapping agents that use MCP is not a Safehouse MCP server.”
SDK packages
Not supported
“Shell CLI only; no official client SDK packages documented.”
Auth documented
Not applicable
“No hosted API account/key authentication; local file/credential access is policy, not service auth.”
Self-serve credentials
Not applicable
“No Safehouse service credentials or account required for local execution.”
Webhooks
Not applicable
“Local wrapper has no hosted event/webhook service.”
CLI tool
Supported
“https://raw.githubusercontent.com/eugene1g/agent-safehouse/main/docs/docs/options.md: official safehouse CLI, full options and execution documentation.”
Error model
Not applicable
“No JSON/HTTP API error model; local policy/command errors only.”
Rate limits documented
Not applicable
“No hosted endpoint rate limits; resource usage belongs to local machine.”
Agent config files
Partially supported
“https://raw.githubusercontent.com/eugene1g/agent-safehouse/main/AGENTS.md: repository LLM quick reference; /agents.md and /.well-known/agent HTTP 404. llm-instructions.txt is an LLM policy-building prompt, not an installable agent skill.”

04 Coding harnesses Which agents and IDEs are documented to run here

Advertised integrations 13

Claude Code Anthropic
Supported
“Tested against all leading agents: Claude Code”
Source agent-safehouse.dev
Codex CLI OpenAI
Supported
“Tested against all leading agents: Codex”
Source agent-safehouse.dev
OpenCode opencode
Supported
“Tested against all leading agents: OpenCode”
Source agent-safehouse.dev
Amp Sourcegraph
Supported
“Tested against all leading agents: Amp”
Source agent-safehouse.dev
GitHub Copilot GitHub
Supported
“Tested against all leading agents: Copilot CLI”
Source agent-safehouse.dev
Gemini CLI Google
Supported
“Tested against all leading agents: Gemini CLI”
Source agent-safehouse.dev
Aider Aider
Supported
“Tested against all leading agents: Aider”
Source agent-safehouse.dev
Goose Block
Supported
“Tested against all leading agents: Goose”
Source agent-safehouse.dev
Pi earendil-works
Supported
“Tested against all leading agents: Pi”
Source agent-safehouse.dev
Cursor Anysphere
Supported
“Tested against all leading agents: Cursor Agent”
Source agent-safehouse.dev
Cline Cline
Supported
“Tested against all leading agents: Cline”
Source agent-safehouse.dev
Kilo Code Kilo
Supported
“Tested against all leading agents: Kilo Code”
Source agent-safehouse.dev
Droid Factory
Supported
“Tested against all leading agents: Droid”
Source agent-safehouse.dev

Plausible compatibility 0

Derived, not stored: the product passes SSH access, so any CLI coding agent is installable inside it. This is plausible compatibility, not a supported integration.

No general shell access documented, so nothing is derived. Absence is not unsupported.

05 Compliance & regions Standards held, with ordinal rigor; never a score

Certifications held 0

No attestations found on the public surface. Empty means nothing is advertised, after checking, not that nothing was checked.

Regions —

No region list captured.

06 Open source Apache-2.0 · fetched by machine, not quoted from marketing

Licence & repository

Licence: Apache-2.0OSI
Primary language: Shell
Stars: 2,104
Forks: 99
Created: 9 Feb 2026
Archived: No

Activity

Last commit: 30 Sep 2026
Latest release: v0.12.0 · 7 Sep 2026
Issues open / closed: 21 / 76 · 78% closed

Eight recent releases span March–September 2026; latest v0.12.0 September 7 follows v0.11.1 July 17 (GitHub creation timestamps).

Fetched via gh on 12 Oct 2026.

Self-hosting

Methods: package-managerother
You operate: macosbashsandbox-exec

Free under Apache-2.0 plus operator hardware and separately installed agent/model usage. macOS-only Seatbelt wrapper; no separate guest kernel, container or hosted tier. Native allowed files remain accessible to the workload; network exfiltration prevention is explicitly not a goal. --enable=launch-services can start unsandboxed host applications. Current main docs narrow workdir to exact invocation directory, unlike stale homepage git-root wording.

Documentation signals 5/8

SupportedQuickstart
Not supportedAPI reference
SupportedSelf-host guide
SupportedChangelog
Not supportedOpenAPI
Not supportedllms.txt
SupportedExamples
SupportedArchitecture doc

07 Company & presence Facts only, not scored

Company

Headquarters: Not disclosed
Founded: —
Team size: Not disclosed
Hiring: unknown

Notable people

eugene1g (repository owner; not asserted legal entity)

Activity

Last release: 0.12.0 — 2026-09-07 raw.githubusercontent.com
Last blog post: —

Presence 3

Links found on the public surface scanned; not an exhaustive search.

08 Sources & method How this entry was produced

Public surface only

Everything here was read from agent-safehouse.dev's unauthenticated pages, docs, pricing and repository on 12 Oct 2026. Nothing behind a login was used.

Statuses, not scores

Capabilities are pass, partial or fail against a written rubric (features v21). “Not assessed” means the scan predates the key.

Confidence is separate

Each fact carries its own confidence. Low-confidence facts are shown, never hidden, so you can weigh them.

Schema: scan v5
Features registry: v21
Keys tracked today: 61
Assessed on this entry: 61

Something wrong on this page?

Nearby in the atlas

All Sandbox products →