UnixShells

HostedPersistent environment

The place where AI agents live — a real Linux machine for Claude Code

Homepage Pricing Repository

Scanned 6 Jun 2026 · Schema v5 · features v9

From: $12/mo
Flat-rate monthly per VM, no metered billing
Free tier: No
Card requirement unconfirmed.
Isolation: Virtual machine
hypervisor, or nothing at all
Regions: —
Managed-shell region placement not disclosed (no user region choice surfaced). The free Relay network spans 9 servers across 3 continents (NAT traversal), but that is not workload placement.
Capabilities: 6 / 48
6 partial · 21 fail · 13 not assessed
Agent readiness: 4/11 · 1/11
read · drive, pre-login surface

Advertised for

AI coding agents · Persistent dev env · Always on services · Docker · Web apps via preview url

Built for

Developers, then technical

· SSH-first, code-first: 'a real Linux machine for Claude Code'
· Real Docker, systemd, iptables, WireGuard — full Linux for developers
· 5 coding agents pre-installed; CLI/terminal-centric access

01 Pricing Flat-rate monthly per VM, no metered billing

Tier	EntryRelay	Shell+
Price	Free (with any account)	$12/mo ($120/yr)
Storage	—	25 GB

per managed VM per month·Card required: unconfirmed·none (flat-rate, no metered billing)·unixshells.com

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

Isolation & lifecycle

Isolation primitive

Virtual machinehypervisor, or nothing at all

Persistence

persistent home dir; overlay resets on restart; sessions persist indefinitely via latch

Snapshots / forks

Resources & limits

Storage

10-25 GB local disk per shell (Shell+ = 25 GB); home dir persists, overlay resets

Limits & quotas

Shell+ = 4 GB RAM / 2 vCPU / 25 GB disk, flat $12/mo (no metered limits); Relay free

GPU

Access

Deploy interface

sshweb-terminalmobile-app

SDK languages

None

Network & secrets

Egress controls

user-controlled (full in-VM iptables/ip), not a platform policy

Secrets

Bring your own cloud

Placement & use

Jurisdiction

not disclosed for shells; relay = 9 servers / 3 continents

Advertised workloads

AI coding agentsPersistent dev envAlways on servicesDockerWeb apps via preview url

03 Capabilities 6 pass · 6 partial · 21 fail · 48 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 1/5

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 assessed

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 assessed

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 supported

Multi-regionCompute placeable in more than one geographic region.

Partially supported

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 assessed

Networking & delivery 4/7

Automatic HTTPSTLS endpoints provisioned automatically per workload.

Partially 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).

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 assessed

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 1/7

Public APIDocumented programmatic API.

Not supported

OpenAPI specMachine-readable OpenAPI / Swagger spec published.

Not supported

CLIOfficial command-line tool.

Partially 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 applicable

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 assessed

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 0/7

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 applicable

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 assessed

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 assessed

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 assessed

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 assessed

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 0/1

Scheduled tasksCron / scheduled job primitive.

Not applicable

Durable workflowsDurable execution / long-running workflow primitive.

Not applicable

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 applicable

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).

Not 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 assessed

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 assessed

Organisation & security 0/5

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

Not applicable

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 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 assessed

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 assessed

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

Partially 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.

Memory-snapshot sub-second boot (200+ tools, no disk/RAM cost)memory-snapshot-boot
“'All of it is loaded into a memory snapshot, so nothing counts against your disk quota and your VM boots in seconds.'” unixshells.com
Mosh-over-WebTransport web terminalmosh-web-terminal
“'The only web terminal that uses Mosh — keystrokes echo instantly, even on slow connections.'” unixshells.com
Persistent session multiplexer (latch)session-persistence-multiplexer
“latch keeps sessions alive across disconnects, reboots, and network changes.” github.com
Native mobile SSH/Mosh app with shell auto-discoverymobile-shell-app
“iOS + Android app; auto-discovers shells; sessions survive network switches.” unixshells.com

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

Can an agent read it?

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

4/11

2 full · 2 partial · 36% of applicable checks

llms.txt
Not supported
“GET /llms.txt 404”
llms-full.txt
Not supported
“No /llms-full.txt”
robots.txt AI policy
Not supported
“robots.txt BLOCKS major AI UAs (ClaudeBot, CCBot, Bytespider, Amazonbot, ...) Disallow: / + Content-Signal: ai-train=no (Cloudflare's AI-crawler-blocking default)”
JSON-LD
Not supported
“No application/ld+json (static HTML site)”
Sitemap
Not supported
“GET /sitemap.xml 404”
Meta tags
Partially supported
“Descriptive <title> + meta description present; OG tags not confirmed”
Markdown negotiation
Not supported
“Static HTML; no .md / markdown content negotiation”
Content efficiency
Supported
“Static HTML 24.8 KB -> 6.8 KB readable (~27.5%) -> >5%”
Docs discoverable
Not supported
“No developer docs section (only per-agent marketing pages)”
Machine-readable pricing
Partially supported
“Pricing on homepage as cards (Relay free, Shell+ $12/mo with specs) — readable but simple marketing prose, not a structured table”
No anti-bot wall
Supported
“Behind Cloudflare but no challenge on public content (homepage 200); only robots blocks training crawlers”

Can an agent drive it?

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

1/11

0 full · 1 partial · 9% of applicable checks

Public API
Not supported
“No public API for programmatic shell creation/management”
OpenAPI spec
Not supported
“No API → no spec”
MCP server
Not supported
“No MCP server”
SDK packages
Not supported
“No platform SDK (OSS repos are standalone tools)”
Auth documented
Not supported
“OPAQUE web login only; no API-auth docs”
Self-serve credentials
Not supported
“Signup -> a VM; no programmatic key issuance”
Webhooks
Not supported
“No webhooks”
CLI tool
Partially supported
“latch (MIT) is an official CLI multiplexer; not a shell-management CLI”
Error model
Not supported
“No API → no error model”
Rate limits documented
Not supported
“No API rate-limit docs”
Agent config files
Not supported
“No agents.md / well-known / skills surface”

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

Advertised integrations 5

Claude Code Anthropic
Supported
“'Run Claude Code on a dedicated VM' — pre-installed, dedicated landing page.”
Source unixshells.com
Codex CLI OpenAI
Supported
“'Give OpenAI Codex ... their own sandbox' — pre-installed, dedicated page.”
Source unixshells.com
OpenCode opencode
Supported
“OpenCode pre-installed, dedicated landing page.”
Source unixshells.com
OpenClaw Peter Steinberger
Supported
“'Run multiple agents in parallel' — OpenClaw pre-installed, dedicated page.”
Source unixshells.com
Aider Aider
Supported
“Aider named among the ~6 pre-installed agents ('Claude Code, OpenClaw, Docker, every major language runtime ... Aider').”
Source unixshells.com

Plausible compatibility 11

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.

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

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 —

Regions are not disclosed on the public surface.

Managed-shell region placement not disclosed (no user region choice surfaced). The free Relay network spans 9 servers across 3 continents (NAT traversal), but that is not workload placement.

07 Company & presence Facts only, not scored

Company

Headquarters: Not disclosed
Founded: —
Team size: small / likely solo (bootstrapped)
Hiring: Unknown

Activity

Last release: OSS components actively pushed (clone VMM 2026-06-05; developer-tools 2026-06-06) github.com
Last blog post: —

Presence 2

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 unixshells.com's unauthenticated pages, docs, pricing and repository on 6 Jun 2026. Nothing behind a login was used.

Statuses, not scores

Capabilities are pass, partial or fail against a written rubric (features v9). “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: v9
Keys tracked today: 61
Assessed on this entry: 48

Something wrong on this page?

Nearby in the atlas

All Persistent environment products →