Skip to content
where do irun this.

Code & AI agent sandboxes: read the guide

sandbox-run

Open source toolSandbox

Run commands in a native Linux namespace sandbox

HomepageDocsRepository

Scanned 9 Oct 2026 · Schema v5 · features v21

Licence
AGPL-3.0

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
3 / 61

4 partial · 49 fail · 0 not assessed

Agent readiness
5/8 · 1/6

read · drive, pre-login surface

Advertised for

Native Linux commands · Untrusted command line applications · AI tools · Local CUDA inference with explicit GPU passthrough

Built for

Developers

  • · https://github.com/sandbox-utils/sandbox-run/blob/master/README.md: CLI-first installation, namespace/capability configuration and shell examples.

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

Isolation & lifecycle

Isolation primitive
Containershares the host kernel
Persistence
Read-write host CWD (unless HOME) and RW_BIND mounts persist; other unmounted state is lost on namespace termination.
Snapshots / forks
No

Resources & limits

Storage
Host bind mounts; ROOT defaults to $PWD/.sandbox; CLEANUP removes ROOT after execution.
Limits & quotas
Not documented
GPU
Optional host NVIDIA device passthrough; CUDA/PyTorch examples require explicit bind mounts.

Access

Deploy interface
cli
SDK languages
None

Network & secrets

Egress controls
Optional slirp4netns --disable-host-loopback; no general egress allowlist documented. Host networking shared without slirp4netns or with PORTS=shared.
Secrets
Sources and exports CWD .env; credentials are visible to the sandboxed workload.
Bring your own cloud
Not documented

Placement & use

Jurisdiction
Not documented
Advertised workloads
Native Linux commandsUntrusted command line applicationsAI toolsLocal CUDA inference with explicit GPU passthrough

02 Capabilities 3 pass · 4 partial · 49 fail · 61 of 61 assessed

  • Supported
  • Partially supported
  • Not supported
  • Not assessed

Compute & storage 1/10

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 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 supported
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 0/9

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 supported
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).
Partially 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 supported

Developer access 1/9

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 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 supported

AI & agents 0/12

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).
Not 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).
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 0/4

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 supported
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 supported
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 supported

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

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

Can an agent read it?

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

5/8

3 full · 2 partial · 63% of applicable checks

  • llms.txt
    Not supported
  • llms-full.txt
    Not supported
  • robots.txt AI policy
    Not applicable
  • JSON-LD
    Not supported
  • Sitemap
    Not applicable
  • Meta tags
    Supported
  • Markdown negotiation
    Partially supported
  • Content efficiency
    Partially supported
  • Docs discoverable
    Supported
  • Machine-readable pricing
    Not applicable
  • No anti-bot wall
    Supported

Can an agent drive it?

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

1/6

1 full · 0 partial · 17% of applicable checks

  • Public API
    Not supported
  • OpenAPI spec
    Not supported
  • MCP server
    Not supported
  • SDK packages
    Not supported
  • Auth documented
    Not applicable
  • Self-serve credentials
    Not applicable
  • Webhooks
    Not applicable
  • CLI tool
    Supported
  • Error model
    Not applicable
  • Rate limits documented
    Not applicable
  • Agent config files
    Not supported

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

Advertised integrations 0

The public surface names no coding harness as supported or documented-to-run-here.

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 AGPL-3.0 · fetched by machine, not quoted from marketing

Licence & repository

Licence
AGPL-3.0OSI
Primary language
Shell
Stars
86
Forks
6
Created
12 Oct 2025
Archived
No
github.com

Activity

Last commit
9 Oct 2026
Latest release
—
Issues open / closed
0 / 1 · 100% closed

GitHub API returned no releases; use the repository source.

Fetched via gh on 9 Oct 2026.

Self-hosting

Methods
other
You operate
linuxposix-shellcoreutilsutil-linuxmount

Install the shell script on PATH. Requires enabled unprivileged user namespaces; README suggests disabling the AppArmor unprivileged-userns restriction. Optional slirp4netns supplies a separate network namespace; otherwise the host network is shared. Guest-to-host gateway access is enabled by default. Automatic seccomp filtering requires optional enosys; an existing custom filter can also be used. No first-party hosting; free under AGPL plus operator-owned infrastructure. Bubblewrap wrapper is separate and has limited feature parity.

Documentation signals 4/8

  • SupportedQuickstart
  • Not supportedAPI reference
  • SupportedSelf-host guide
  • Not 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

Activity

Last release
— github.com
Last blog post
—

Presence 1

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 github.com/sandbox-utils/sandbox-run's unauthenticated pages, docs, pricing and repository on 9 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 →
where do i run this.

An independent spec sheet for places to run code, and the code your agents write. Facts come from each product's public pages; every capability is a count, never a grade.

Verify

Pages change; so do prices. Verify on the vendor's site before you commit; every product page shows when it was read.

Where Do I Run This © 2026counts, not grades · public pages only