ShellBox

HostedPersistent environment

Instant Linux boxes via SSH — create, duplicate, scale to zero; pay per minute running, $0.50/mo parked, no subscription

Homepage Docs Pricing Repository

Scanned 15 Oct 2026 · Schema v5 · features v21

From: —
Pre-paid balance; per-minute billing while running + flat monthly while stopped (parked); no subscription
Free tier: No
Card requirement unconfirmed.
Isolation: Firecracker microVM
shares only the hypervisor
Regions: 1
Helsinki, Finland (Hetzner auction servers)
Capabilities: 16 / 61
2 partial · 43 fail · 0 not assessed
Agent readiness: 7/11 · 7/11
read · drive, pre-login surface

Advertised for

Dev environments · CI runners · Daemons bots · AI agent sandbox · Scheduled jobs cron · Web services scale to zero

Built for

Developers, then technical

· SSH-only control plane (`ssh shellbox.dev <verb>`), no web dashboard
· Account = SSH key fingerprint; --json contract for scripting
· Per-minute compute + Firecracker/Cloud-Hypervisor / btrfs-reflinks vocabulary

01 Pricing Pre-paid balance; per-minute billing while running + flat monthly while stopped (parked); no subscription

Tier	EntryPay-as-you-go (per slot size)
Price	x1 $0.02/hr running · $0.50/mo parked (sizes scale linearly to x8)
Includes	no subscription; pre-paid balance (min $10 top-up); 16 running / 64 total slots; per-minute billing; auto-stop < $5, auto-delete at $0; no backups, no SLA
Compute hours overage	$0.02/h

running $/hr by slot size (per-minute, rounded up) + stopped $/mo by slot size·Card required: unconfirmed·shellbox.dev

Overages: x1 $0.02/hr running / $0.50/mo parked; doubling per size to x8 ($0.16/hr / $4.00/mo); per-minute billing rounded up

02 Website design Desktop public website · assessed 15 Oct 2026

Complete assessment.

A centered amber-on-black terminal interface unifies landing, pricing and API tabs, with ASCII branding, monospace command examples, fine rectangular borders and animated falling glyphs. All three public desktop roles captured on one official document.

Retro-computing

Landing page: captured
Pricing: captured
Docs: captured

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

Isolation & lifecycle

Isolation primitive

Firecracker microVMshares only the hypervisor

Persistence

Persistent boxes; pause-on-disconnect (120s grace) → memory snapshot to disk → resume (~3s) restores processes/shell-history/files; stopped boxes parked at $0.50/mo (x1)

Snapshots / forks

Yes

Resources & limits

Storage

50 GB SSD baseline (x1) → 400 GB (x8); fixed at box creation (delete+recreate to resize); no backups

Limits & quotas

16 running slots / 64 total slots per account (xN box = N slots); 200 SSH connections/min/IP; per-minute billing rounded up; auto-stop < $5 balance, auto-delete at $0

GPU

Access

Deploy interface

clicontainer-image

SDK languages

None

Network & secrets

Egress controls

Secrets

none managed — SSH key fingerprint is the only credential; no secrets vault/injection

Bring your own cloud

Placement & use

Jurisdiction

EU — Hetzner Finland; one workload region

Advertised workloads

Dev environmentsCI runnersDaemons botsAI agent sandboxScheduled jobs cronWeb services scale to zero

04 Capabilities 16 pass · 2 partial · 43 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 6/11

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).

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.

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.

Supported

GPU computeGPU-backed instances available.

Not supported

Multi-regionCompute placeable in more than one geographic region.

Not supported

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

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.

Supported

Networking & delivery 6/9

Automatic HTTPSTLS endpoints provisioned automatically per workload.

Supported

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

Supported

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

Supported

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

Supported

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

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).

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.

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 3/10

Public APIDocumented programmatic API.

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.

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 supported

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 1/6

Scheduled tasksCron / scheduled job primitive.

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 supported

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 0/9

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

Not supported

SSO / SAMLEnterprise single sign-on.

Not supported

Secrets managementFirst-class secrets storage / injection.

Not supported

TeamsMulti-user team accounts.

Not supported

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

Partially supported

BYOCRuns inside the customer's own cloud account.

Not supported

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 supported

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.

Not 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.

SSH-only control plane — account = SSH key fingerprint; every operation via `ssh shellbox.dev <verb>` with a stable, additive-only --json contractssh-control-plane
“No REST endpoints, no API tokens, no SDK. Your SSH key fingerprint is your account.” shellbox.dev

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

Can an agent read it?

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

7/11

3 full · 4 partial · 64% of applicable checks

llms.txt
Not supported
“GET /llms.txt 404”
llms-full.txt
Not supported
“GET /llms-full.txt 404”
robots.txt AI policy
Partially supported
“Fresh robots.txt: User-agent: *; empty Disallow; no AI-specific policy, default allow.”
JSON-LD
Not supported
“0 application/ld+json blocks on the homepage”
Sitemap
Partially supported
“sitemap.xml present but trivial (single URL — the homepage)”
Meta tags
Partially supported
“Fresh homepage has descriptive title and description but no OG metadata; not the complete title+description+OG required for full credit.”
Markdown negotiation
Not supported
“Accept: text/markdown returns the same HTML (server ignores header); no .md variant”
Content efficiency
Supported
“Raw HTML 112552 bytes contains substantive inline API/FAQ/legal/blog content (>5% readable text), not an empty app shell; fresh rendered evidence retained.”
Docs discoverable
Partially supported
“API/FAQ are prominent tab buttons; API text is inline in HTML, but selecting hidden tab panels requires JavaScript. No ordinary docs nav anchor without JS.”
Machine-readable pricing
Supported
“Fresh browser-rendered structured slot table x1–x8 and calculator; raw table rows generated by inline JS rather than present as rows in initial HTML.”
No anti-bot wall
Supported
“Fresh homepage and anonymous browser role views fetched without a challenge; missing well-known/spec paths return ordinary 404.”

Can an agent drive it?

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

7/11

4 full · 3 partial · 64% of applicable checks

Public API
Supported
“Fresh API tab documents all SSH management verbs with exact response schemas and stable --json contract. Public API is transport-neutral; absence of HTTP is not absence of a documented programmatic API.”
OpenAPI spec
Not supported
“No OpenAPI (SSH-only); --json schema via `ssh shellbox.dev help --json`”
MCP server
Not supported
“No MCP; /.well-known/mcp 404”
SDK packages
Not supported
“No SDK — explicitly 'no SDK'”
Auth documented
Supported
“Auth fully documented: SSH key fingerprint = account; key add/remove/list; PQ-hybrid KEX; DNSSEC SSHFP to skip TOFU”
Self-serve credentials
Supported
“First SSH connection creates account from public key fingerprint; key add/remove documented. Funding still requires Paddle checkout ($10 min); no paid runtime exercised.”
Webhooks
Partially supported
“Inbound HTTP callbacks documented (cron → POST /cron on box; email → POST /email on box); no outbound event webhooks”
CLI tool
Supported
“The SSH verbs ARE the official CLI (`ssh shellbox.dev <verb>`)”
Error model
Partially supported
“FAQ: Errors still print as text to stderr with a non-zero exit code. Check exit code first, then parse stdout as JSON. No structured JSON error object model.”
Rate limits documented
Partially supported
“200 SSH connections/min/IP documented; no API response-header rate-limit docs”
Agent config files
Not supported
“No agents.md / .well-known/agent / skills listing”

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

Advertised integrations 2

Claude Code Anthropic
Supported
“If you run a coding agent (Claude Code, Codex, etc.) inside a keepalive box, you can have it stop the box when the task is complete.”
Source shellbox.dev
SSH-accessible; 'standard SSH that every agent framework already supports' (March 2026 blog).
Codex CLI OpenAI
Supported
“If you run a coding agent (Claude Code, Codex, etc.) inside a keepalive box ...”
Source shellbox.dev
Same SSH-into-a-box agent workflow.

Plausible compatibility 13

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.

Aider
Amp
Antigravity
Devin
Droid
Gemini CLI
Goose
Hermes Agent
Kilo Code
Kiro CLI
OpenCode
Pi
Qwen Code

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

Certifications held 1

GDPR
self-attestedhosted
“EU-operated (Finland); GDPR rights (access, rectification, erasure, portability); no cookies, no email collected, SSH-key-only identity, 30-day IP logs.”
Source shellbox.devConfidence: medium

Regions 1

Helsinki, Finland (Hetzner auction servers)helsinki

Official infra tab: Bare metal in Hetzner Finland (EU). One region today; more on demand. No second region advertised.

Legal

Privacy notice Terms of service

08 Company & presence Facts only, not scored

Company

Headquarters: Undisclosed; EU-operated service with Finland governing law and hosting
Founded: Public product blog dates to January 2026; legal founding undisclosed
Team size: Undisclosed
Hiring: No public hiring page found

Activity

Last release: Latest advertised update: 2026-04-08 — Cloud Hypervisor backend and stable JSON interface shellbox.dev
Last blog post: 2026-04-08 — New Features for April 8th, 2026 shellbox.dev

Presence 3

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 shellbox.dev's unauthenticated pages, docs, pricing and repository on 15 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 Persistent environment products →