Code & AI agent sandboxes: read the guide

Agent37

HostedSandbox

Host any agent harness.

Homepage Docs Pricing

Scanned 12 Oct 2026 · Schema v5 · features v21

From: —
Prepaid, per-minute compute + reserved disk
Free tier: Not documented
One-time $5 starter credit; no recurring free tier
Isolation: Kata / gVisor
hardened or user-space kernel
Regions: 1
United States
Capabilities: 23 / 61
7 partial · 31 fail · 0 not assessed
Agent readiness: 11/11 · 9/11
read · drive, pre-login surface

Advertised for

Agents · Code execution · Web apps · Desktop/browser automation · Docker/Kubernetes/databases in VM mode

Built for

Developers, then semi-technical builders

· https://www.agent37.com/docs/agents-api/overview: REST examples and one-instance-per-user integration pattern.

01 Pricing Prepaid, per-minute compute + reserved disk

Tier	EntryDefault sandbox	Performance sandbox	TopFull VM
Price	$4.76/month: 2 vCPU, 4 GB RAM, 4 GB disk always on	$17.96/month: 2 vCPU, 4 GB RAM, 4 GB disk always on	$11.36/month: 2 vCPU, 4 GB RAM, 4 GB disk always on
Storage overage	$0.09/GB	$0.09/GB	$0.09/GB
vCPU hours overage	$0.00109589/h	$0.00438356/h	$0.00273973/h
Memory gb hours overage	$0.0009589/h	$0.00383562/h	$0.00239726/h

Free tier: One-time $5 starter credit; no recurring free tier

vCPU-hours, RAM GB-hours, disk GB-month·Card required: Yes·agent37.com

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

Isolation & lifecycle

Isolation primitive

Kata / gVisorhardened or user-space kernel

Persistence

Sandbox /home/node; full disk in VM mode

Snapshots / forks

Nightly seven-slot backups, manual backup/restore, disk forks

Resources & limits

Storage

2–80 GB shape-dependent disk; $0.09/GB-month

Limits & quotas

2/4, 4/8, 8/16, 16/32 vCPU/RAM GB. Held instances: 1 on credit, 10 after top-up, 50 at $100, 200 at $250

GPU

Not documented

Access

Deploy interface

docker-imagedockerfileapidashboardtemplatesshcli

SDK languages

None

Network & secrets

Egress controls

Fixed public-internet-only egress firewall

Secrets

Write-only environment variables at create and PATCH; build secrets

Bring your own cloud

Not documented

Placement & use

Jurisdiction

United States

Advertised workloads

AgentsCode executionWeb appsDesktop/browser automationDocker/Kubernetes/databases in VM mode

03 Capabilities 23 pass · 7 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 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.

Partially 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.

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 3/9

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.

Partially 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).

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.

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 4/10

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.

Supported

Git deployDeploy from a Git repo / push-to-deploy.

Not supported

Private container registryHosted private image registry.

Partially 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 5/12

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

Not supported

Agent skillsInstallable / declarable agent skills or tools.

Supported

AI app builderPrompt-to-app / vibe-coding generation surface.

Partially supported

MCP serverExposes a Model Context Protocol server for agents.

Partially 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).

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).

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).

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 2/6

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).

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 3/9

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

Supported

SSO / SAMLEnterprise single sign-on.

Not supported

Secrets managementFirst-class secrets storage / injection.

Supported

TeamsMulti-user team accounts.

Not supported

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

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

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

Can an agent read it?

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

11/11

5 full · 6 partial · 100% of applicable checks

llms.txt
Supported
“https://www.agent37.com/docs/llms.txt: substantive documentation index, billing and API links.”
llms-full.txt
Supported
“https://www.agent37.com/docs/llms-full.txt: 735097 bytes; comprehensive docs retained by pointer and individual pages.”
robots.txt AI policy
Partially supported
“https://www.agent37.com/robots.txt: User-agent: *; empty Disallow; no AI-specific policy.”
JSON-LD
Partially supported
“https://www.agent37.com/: Organization JSON-LD.”
Sitemap
Partially supported
“https://www.agent37.com/sitemap.xml: small sitemap; additional blog/docs sitemap pointers in robots.”
Meta tags
Supported
“https://www.agent37.com/: descriptive title, description and OpenGraph metadata.”
Markdown negotiation
Partially supported
“https://www.agent37.com/docs/agents-api/overview.md: markdown available; homepage Accept text/markdown returns HTML.”
Content efficiency
Partially supported
“https://www.agent37.com/: 8730/206379 readable/HTML bytes, between 1 and 5 percent.”
Docs discoverable
Supported
“https://www.agent37.com/: Docs nav link.”
Machine-readable pricing
Supported
“https://www.agent37.com/docs/agents-api/billing: structured CPU/RAM/disk rates and shapes.”
No anti-bot wall
Partially supported
“Main site/docs fetchable. Trust portal initially returned HTTP 403; foxcrawl rendered overview, compliance and resources with HTTP 200 and blocked=false on 2026-10-12. Half credit retained for path-specific direct-fetch blocking, not missing portal evidence.”

Can an agent drive it?

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

9/11

6 full · 3 partial · 82% of applicable checks

Public API
Supported
“https://www.agent37.com/docs/agents-api/overview: documented Sandbox and Agent REST APIs.”
OpenAPI spec
Not supported
“Docs/root/API conventional spec probes did not return OpenAPI; docs overview/index did not link a fetchable spec.”
MCP server
Supported
“https://www.agent37.com/docs/agents-api/managed-services: documented hosted /mcp/composio and /mcp/perflo endpoints; integration tools only, inside hosted instances, not lifecycle control.”
SDK packages
Not supported
“https://www.agent37.com/docs/agents-api/overview: curl, Python requests and Node fetch examples; no official SDK packages found.”
Auth documented
Supported
“https://www.agent37.com/docs/agents-api/concepts: workspace keys, instance tokens, signed URLs and key IP allowlisting.”
Self-serve credentials
Partially supported
“https://www.agent37.com/docs/agents-api/quickstart: dashboard key/wallet setup; no programmatic issuance found.”
Webhooks
Partially supported
“https://www.agent37.com/docs/agents-api/hermes-webhooks: signed inbound third-party Hermes webhooks, not a platform lifecycle event subscription API.”
CLI tool
Supported
“https://www.agent37.com/docs/agents-api/ssh: official npm agent37 SSH/tunnel CLI.”
Error model
Supported
“https://www.agent37.com/docs/agents-api/errors: documented error code/message and HTTP statuses.”
Rate limits documented
Supported
“https://www.agent37.com/docs/agents-api/errors: backup 15-minute limit and Retry-After header; scope is endpoint-specific.”
Agent config files
Partially supported
“https://www.agent37.com/docs/for-agents: one agent-oriented instructions surface; conventional agents.md and well-known agent absent.”

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

Advertised integrations 7

Claude Code Anthropic
Supported
“| `agent37-claude-code` | Claude Code, Anthropic's coding agent, on your own Anthropic account: chat, code, files, shell. No browser or desktop. |”
Source agent37.com
Codex CLI OpenAI
Supported
“| `agent37-codex` | Codex, OpenAI's coding agent, on your own OpenAI account: chat, code, files, shell. No browser or desktop. |”
Source agent37.com
OpenCode opencode
Supported
“| `agent37-opencode` | OpenCode, SST's open-source coding agent, on the managed model out of the box: chat, code, files, shell. No browser or desktop. |”
Source agent37.com
Pi earendil-works
Supported
“| `agent37-pi` | Pi, the minimal open-source agent harness, on the managed model out of the box: chat, code, files, shell. No browser or desktop. |”
Source agent37.com
Hermes Agent Nous Research
Supported
“| `agent37-hermes` | Hermes, the general agent: chat, browsing, code, files. The default. |”
Source agent37.com
OpenClaw Peter Steinberger
Supported
“| `agent37-openclaw` | OpenClaw, the general agent: chat, headless browsing, code, files. |”
Source agent37.com
Cursor Anysphere
Supported
“Run the tool calls of Cursor Cloud Agents on an always-on Agent37 instance: Cursor runs the agent, your instance runs every command and keeps the checkout.”
Source agent37.com

Plausible compatibility 10

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
Kilo Code
Kiro CLI
Qwen Code

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

Certifications held 2

SOC 2 Type II
in-progresshosted
“SOC 2 Type II is in progress, and our controls are monitored continuously. The scope covers the Agent 37 Cloud API, managed agent hosting, our dashboard, and the infrastructure that runs them.”
Source agent37.com
GDPR
in-progresshosted
“GDPR In progress”
Source trust.agent37.com

Rendered trust portal (https://trust.agent37.com/compliance, foxcrawl 2026-10-12) lists SOC 2 and GDPR as In progress; it does not distinguish SOC 2 types. Homepage/privacy claims a SOC 2 Type I report and says Type II is in progress. Type I claim retained here, not as certified: the rendered portal does not confirm a completed audit. Type II in-progress row is supported by the privacy page. Resources lists access-controlled policies and a System Description; no audit report was inspected. Portal access succeeded; compliance evidence remains vendor-reported, with the Type I claim unresolved.

Regions 1

United States

Dedicated US servers; Cloudflare edge is not multi-region compute.

Legal

Privacy notice Terms of service

07 Company & presence Facts only, not scored

Company

Headquarters: Not disclosed
Founded: —
Team size: Not disclosed
Hiring: Unknown

Activity

Last release: — agent37.com
Last blog post: 2026-10-12 agent37.com

Presence 3

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 agent37.com's unauthenticated pages, docs, pricing and repository on 12 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 →