Code & AI agent sandboxes: read the guide

Superconductor

HostedSandbox

The multiplayer AI workspace for teams and coding agents

Homepage Docs Pricing

Scanned 15 Oct 2026 · Schema v5 · features v21

From: $128/mo
Workspace compute subscription plus sandbox-hour overages; no per-seat charge. Bring model subscriptions/API keys separately. Pro currently activated through an onboarding call.
Free tier: Not documented
Free: 32 sandbox-hours/month, 4 members, 4 concurrent agents, up to 4 vCPU/8GB.
Isolation: Container
shares the host kernel
Regions: 1
AWS US regions
Capabilities: 16 / 61
8 partial · 37 fail · 0 not assessed
Agent readiness: 8.5/11 · 0/11
read · drive, pre-login surface

Advertised for

Parallel coding agents · Isolated development environments · Live app previews · QA checks · Agent benchmarking · Scheduled agent tasks

Built for

Technical, then semi-technical builders

· Engineering teams working on real codebases (GitHub repos, Docker Compose, Rails/Next/etc.)
· GUI/mobile/Slack-first operation — explicitly NOT CLI/API/SSH (no public API)
· Multiplayer team workspace (RBAC, shared sessions) rather than a solo-dev tool

01 Pricing Workspace compute subscription plus sandbox-hour overages; no per-seat charge. Bring model subscriptions/API keys separately. Pro currently activated through an onboarding call.

Tier	EntryFree	Pro (selected 512 sandbox-hours)	TopEnterprise
Price	$0/month	$128/month	Custom
Seats	4	32	—
vCPU hours	32 h	512 h	—

Free tier: Free: 32 sandbox-hours/month, 4 members, 4 concurrent agents, up to 4 vCPU/8GB.

sandbox-hour (1 vCPU / 2GB RAM for one hour), metered per second·Card required: No·$30 / 100 sandbox-hours; monthly allowance does not roll over.·superconductor.com

02 Website design Desktop public website · assessed 15 Oct 2026

Complete assessment.

Dark atmospheric navy marketing and pricing pages use broad centered typography and rounded controls; documentation switches to a light three-column reading interface. All three desktop roles captured; incomplete document images noted.

Corporate

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

Containershares the host kernel

Persistence

Filesystem retained across automatic idle pause; running processes stop and startup commands rerun on resume. Not an attachable durable-volume product.

Snapshots / forks

Saved project filesystem snapshots seed fresh implementations; build failures retain the last completed snapshot. No live memory/process checkpoint guarantee.

Resources & limits

Storage

Configurable sandbox disk. Pricing says 2–16 GB; development-environment docs say 2–20 GB. Files persist through idle pause, but not a separately managed volume.

Limits & quotas

Free: 32 sandbox-hours/month, 4 vCPU/8GB, 4 members and 4 concurrent agents. Pro: 8 vCPU/32GB, 32 members and unlimited concurrency. Enterprise: 16 vCPU/64GB, unlimited members/concurrency, custom compute allowance. 15-minute preview idle pause. Resource docs have older 8 CPU/16GB limits.

GPU

Access

Deploy interface

dashboard

SDK languages

None

Network & secrets

Egress controls

Strong: per-project network sandboxing with 3 modes (no-access / custom-allowlist / full), per-domain rules with wildcards + read-only (GET/HEAD/OPTIONS) flag, curated package-registry allowlist; default = custom-access with trusted registries.

Secrets

Encrypted project/workspace credentials; exported secrets reach build/startup/terminal/agent environments; inline secret substitutions scoped to command block. Short-lived workload identity JWT available via SC_IDENTITY_TOKEN_FILE.

Bring your own cloud

Enterprise: deploy sandboxes in your own cloud or private infrastructure; contact sales.

Placement & use

Jurisdiction

United States (AWS US regions)

Advertised workloads

Parallel coding agentsIsolated development environmentsLive app previewsQA checksAgent benchmarkingScheduled agent tasks

04 Capabilities 16 pass · 8 partial · 37 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 3/11

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 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.

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.

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.

Not supported

Networking & delivery 4/9

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.

Not 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.

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).

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.

Partially 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 0/10

Public APIDocumented programmatic API.

Not supported

OpenAPI specMachine-readable OpenAPI / Swagger spec published.

Not supported

CLIOfficial command-line tool.

Not 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.

Partially 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 4/12

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

Partially supported

Agent skillsInstallable / declarable agent skills or tools.

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.

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.

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).

Partially 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).

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).

Partially 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 4/9

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

Not supported

SSO / SAMLEnterprise single sign-on.

Not supported

Secrets managementFirst-class secrets storage / injection.

Supported

TeamsMulti-user team accounts.

Supported

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

Supported

BYOCRuns inside the customer's own cloud account.

Partially 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).

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.

Parallel implementation recommendationsparallel-agent-comparison
“Automatically compare multiple implementations and get a recommendation for the best one.” superconductor.com
AI-guided code reviewai-guided-code-review
“Walks through changes file-by-file in logical order.” superconductor.com
Agent benchmarking on your codebaseagent-benchmarking
“Define ground-truth pull requests and compare coding agents.” superconductor.com
Email and meeting to agent automationsignal-to-code-automation
“Meeting assistant creates and links tickets in real time.” superconductor.com

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

Can an agent read it?

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

8.5/11

7 full · 3 partial · 77% of applicable checks

llms.txt
Supported
“Apex llms.txt links product, pricing, docs bundle and company pages.”
llms-full.txt
Supported
“/docs/llms-full.txt returns comprehensive full documentation; bounded excerpt retained with individual cited pages.”
robots.txt AI policy
Partially supported
“robots.txt default allow; no explicit AI policy.”
JSON-LD
Partially supported
“WebSite and Organization JSON-LD only; no Product offers.”
Sitemap
Supported
“sitemap.xml links public-pages, blog and docs sitemaps; public-pages and docs child maps fetched.”
Meta tags
Supported
“Descriptive title, description, OpenGraph and Twitter tags.”
Markdown negotiation
Not supported
“Accept text/markdown returned HTTP 406; docs quick-start.md returned 404.”
Content efficiency
Partially supported
“12252 readable text bytes / 400735 HTML bytes = 3.1%.”
Docs discoverable
Supported
“'Docs' first-class in header nav; /docs is a real docs site with quick-start, comparison, etc.”
Machine-readable pricing
Supported
“Public pricing HTML contains Free/Pro/Enterprise tiers and sandbox-hour/overage terms.”
No anti-bot wall
Supported
“No challenge on public content — homepage, /docs, /security, /blog all fetched 200 headlessly”

Can an agent drive it?

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

0/11

0 full · 0 partial · 0% of applicable checks

Public API
Not supported
“Fresh full documentation index and product pages expose UI/integration workflows, but no public platform API/SDK/CLI/MCP-control/discovery contract. /.well-known/mcp.json and /openapi.json returned 404. Agent outbound MCP support is not a platform MCP server.”
OpenAPI spec
Not supported
“No API -> no spec”
MCP server
Not supported
“No first-party MCP control server (MCP support is for the coding agents it runs, scored as the mcp-client feature)”
SDK packages
Not supported
“No SDK”
Auth documented
Not supported
“OAuth login + provider-key management, but no public API-auth docs”
Self-serve credentials
Not supported
“No platform API/key issuance — you bring your own agent provider keys via a human signup”
Webhooks
Not supported
“No public webhooks (Slack/GitHub are inbound integrations)”
CLI tool
Not supported
“No CLI (GUI desktop app instead)”
Error model
Not supported
“No public API -> no error model”
Rate limits documented
Not supported
“No public API rate-limit docs”
Agent config files
Not supported
“No agents.md / well-known / skills surface for OPERATING Superconductor (its skill/MCP support configures the coding agents it runs)”

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

Advertised integrations 7

Claude Code Anthropic
Supported
“Claude Code listed as a supported cloud coding agent.”
Source superconductor.com
Codex CLI OpenAI
Supported
“Codex listed as a supported cloud coding agent.”
Source superconductor.com
Amp Sourcegraph
Supported
“Amp listed as a supported cloud coding agent.”
Source superconductor.com
OpenCode opencode
Supported
“OpenCode listed as a supported cloud coding agent.”
Source superconductor.com
Droid Factory
Supported
“Factory Droid listed as a supported cloud coding agent.”
Source superconductor.com
Pi earendil-works
Supported
“Pi listed as a supported cloud coding agent.”
Source superconductor.com
Cursor Anysphere
Supported
“Cursor listed as a supported cloud coding agent.”
Source superconductor.com

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.

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

Certifications held 3

SOC 2 Type II
in-progresshosted
“'Working toward SOC 2 Type 2 compliance ... ongoing initiative with no guaranteed timeline.'”
Source superconductor.com
CCPA
self-attestedhosted
“'CCPA compliance for California residents.'”
Source superconductor.com
GDPR
self-attestedhosted
“'GDPR-aware practices for EU users'; 72h supervisory-authority notification where required.”
Source superconductor.com

Regions 1

AWS US regionsUnited States

Managed cloud security policy discloses AWS US regions for hosting/data/backups. No regional selector documented. Enterprise additionally advertises own-cloud/private sandbox deployment; residency details require sales confirmation.

Legal

Privacy notice Terms of service

08 Company & presence Facts only, not scored

Company

Headquarters: San Francisco, CA (2261 Market Street #4795, 94114)
Founded: —
Team size: 8 named team members on About; Careers still says team of 7
Hiring: Hiring: Principal Web Developer (Rails), Head of Developer Relations, Agent Maestro

Notable people

Arjun Singh — cofounder/CEO
Sergey Karayev — cofounder
Kevin Gutowski — cofounder
Founders met as Berkeley AI PhDs and co-founded Gradescope

Activity

Last release: Weekly Changelog: October 4–10 (2026-10-10) superconductor.com
Last blog post: 2026-10-10 superconductor.com

Presence 5

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 superconductor.com'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 Sandbox products →