Code & AI agent sandboxes: read the guide
Anthropic Sandbox Runtime (srt)
Open source toolSandboxA lightweight sandboxing tool for enforcing filesystem and network restrictions on arbitrary processes at the OS level, without requiring a container.
Scanned 26 Oct 2026 · Schema v5 · features v21
- Licence
- Apache-2.0
Self-hosted; you pay for the infrastructure.
- Free tier
- Free to run
- Isolation
- Container
shares the host kernel
- Regions
- —
Not disclosed on the public surface.
- Capabilities
- 7 / 61
3 partial · 31 fail · 0 not assessed
- Agent readiness
- 4/5 · 3/6
read · drive, pre-login surface
Advertised for
Arbitrary shell commands · Agent generated code · Local MCP servers
Built for
Developers, then technical
- · https://github.com/anthropics/sandbox-runtime/blob/main/README.md — CLI/library-first setup and OS security configuration.
01 Website design Desktop public website · assessed 26 Oct 2026
Complete assessment.
GitHub-only desktop public surface: compact repository table/sidebar and text-led README with neutral colors and restrained borders, not a standalone branded product site.
- Landing page: captured
- Docs: captured
- Pricing: not applicable
02 Runtime Each fact carries its source; dots show confidence. Open a row for the evidence.
Isolation & lifecycle
Isolation primitive
Containershares the host kernel
Persistence
Allowed writes go to the operator filesystem; no managed disk lifecycle. Linux read-denied directory tmpfs output is lost at exit.
Snapshots / forks
No runtime snapshot, fork or memory restore documented.
Resources & limits
Storage
Host paths with configured read/write rules; no object storage or managed volumes.
Limits & quotas
Host-dependent, no hosted quotas. Beta research preview; APIs/configuration may change. Windows alpha limitations and Linux namespace/seccomp caveats documented.
GPU
No GPU instance provisioning; host hardware is operator-owned.
Access
Deploy interface
clisdk
SDK languages
TypeScriptJavaScript
Network & secrets
Egress controls
Default-deny domain allowlist/denylist via HTTP and SOCKS5 proxies, resolved-address checks, optional request filtering and TLS termination. Platform-specific weaker modes and Windows gaps apply.
Secrets
credentials.envVars/files deny or mask; sentinel substituted on permitted egress, optional SigV4 signing. Masking requires TLS termination; platform differences apply.
Bring your own cloud
na
Placement & use
Jurisdiction
na
Advertised workloads
Arbitrary shell commandsAgent generated codeLocal MCP servers
03 Capabilities 7 pass · 3 partial · 31 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 0/7
Persistent diskStorage that survives restart/stop (not ephemeral-only).
Partially 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 applicable
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.
Not applicable
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 supported
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 supported
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 1/2
Automatic HTTPSTLS endpoints provisioned automatically per workload.
Not applicable
Built-in reverse proxyPlatform routes external traffic to workload services.
Not applicable
Custom domainsBring-your-own domain via CNAME/DNS.
Not applicable
Public preview URLsShareable per-deploy / per-branch URLs.
Not applicable
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).
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 applicable
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 3/8
Public APIDocumented programmatic API.
Supported
OpenAPI specMachine-readable OpenAPI / Swagger spec published.
Not supported
CLIOfficial command-line tool.
Supported
SDKOfficial client library/libraries.
Supported
SSH accessDirect SSH into workloads.
Not supported
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 supported
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 2/12
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).
Supported
LLM gatewayRoutes LLM API calls through the platform (multi-provider).
Not supported
BYOK for LLMsBring-your-own LLM provider keys.
Not 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 supported
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).
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 0/0
First-party databasePlatform-provided managed database.
Not applicable
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.
- Filesystem read/write and Unix socket policyfilesystem-access-policy
“Filesystem restrictions: Control which files/directories can be read/written; Unix socket restrictions: Control access to local IPC sockets.” github.com
- Live network configuration channellive-egress-policy-update
“--control-fd <fd> reads config updates ... network lists ... take effect on the next connection ... Nothing else changes.” github.com
04 Agent readiness Pre-login surface · counts, not a grade
Can an agent read it?
parse-ability · docs, metadata, machine-readable surfaces
4/5
3 full · 1 partial · 80% of applicable checks
- llms.txtNot applicable
- llms-full.txtNot applicable
- robots.txt AI policyNot applicable
- SitemapNot applicable
- JSON-LDNot supported
- Meta tagsSupported
- Markdown negotiationPartially supported
- Content efficiencyNot applicable
- Docs discoverableSupported
- Machine-readable pricingNot applicable
- No anti-bot wallSupported
Can an agent drive it?
act-ability · APIs, SDKs, MCP, credentials, webhooks
3/6
2 full · 1 partial · 50% of applicable checks
- Public APISupported
- OpenAPI specNot applicable
- MCP serverNot supported
- SDK packagesPartially supported
- Auth documentedNot applicable
- Self-serve credentialsNot applicable
- WebhooksNot applicable
- CLI toolSupported
- Error modelNot supported
- Rate limits documentedNot applicable
- Agent config filesNot supported
05 Coding harnesses Which agents and IDEs are documented to run here
Advertised integrations 1
- Claude Code AnthropicSupported
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.
06 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.
07 Open source Apache-2.0 · fetched by machine, not quoted from marketing
Licence & repository
- Licence
- Apache-2.0OSI
- Primary language
- TypeScript
- Stars
- 6,645
- Forks
- 587
- Created
- 20 Oct 2025
- Archived
- No
Activity
- Last commit
- 25 Oct 2026
- Latest release
- v0.0.81 · 20 Oct 2026
- Issues open / closed
- 136 / 40 · 23% closed
Eight releases from August 25 through October 20; roughly weekly to fortnightly. Current main ahead of release.
Fetched via gh on 26 Oct 2026.
Self-hosting
- Methods
- package-managersource-build
- You operate
- nodejsbubblewrapsocatripgrep
Free Apache-2.0 software plus operator hardware/infra. Node >=22.12.0. Linux needs bubblewrap, socat and ripgrep; macOS uses built-in sandbox-exec; Windows alpha requires one-time elevated install and dedicated shared machine account. This is not a VM or managed multitenant service. Default reads unrestricted: configure denyRead/credentials. Seccomp/socket and namespace protection have architecture/version/weaker-mode caveats; Ubuntu user namespace restrictions may require host configuration. Windows Schannel clients fail; shared-account ACL and impersonation/service-mediated network gaps are documented. Current-main capabilities may postdate npm v0.0.81.
Documentation signals 5/8
- SupportedQuickstart
- SupportedAPI reference
- SupportedSelf-host guide
- Not supportedChangelog
- Not supportedOpenAPI
- Not supportedllms.txt
- SupportedExamples
- SupportedArchitecture doc
08 Company & presence Facts only, not scored
Company
- Headquarters
- Not disclosed
- Founded
- —
- Team size
- Not disclosed
- Hiring
- Unknown
Activity
- Last release
- v0.0.81 — 2026-10-20 github.com
- Last blog post
- — github.com
Presence 2
Links found on the public surface scanned; not an exhaustive search.
09 Sources & method How this entry was produced
Public surface only
Everything here was read from github.com/anthropics/sandbox-runtime's unauthenticated pages, docs, pricing and repository on 26 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?
