Code & AI agent sandboxes: read the guide
Scanned 5 Jun 2026 · Schema v5 · features v3
- From
- —
Graduated usage — vCPU-hour billing (rate drops with monthly volume) + volume storage; pausing a VM stops the meter; no subscription
- Free tier
- No
Card requirement unconfirmed.
- Isolation
- Virtual machine
hypervisor, or nothing at all
- Regions
- —
Only region 'sfo' (San Francisco) appears — in the boot-time benchmark — not as a selectable placement. No region matrix or data-residency disclosed → disclosed:false.
- Capabilities
- 10 / 35
5 partial · 19 fail · 26 not assessed
- Agent readiness
- 10/11 · 7/11
read · drive, pre-login surface
Advertised for
Reinforcement learning · AI coding agents · Browser automation · Non deterministic computer use
Built for
Developers, then technical
- · API/SDK-first (REST + Python/TS, console-token WebSocket TTY)
- · Fetchable OpenAPI 3.1 + llms.txt/llms-full + machine-readable pricing
- · vCPU-hour usage billing; microVM / dedicated-kernel vocabulary
01 Pricing Graduated usage — vCPU-hour billing (rate drops with monthly volume) + volume storage; pausing a VM stops the meter; no subscription
| Tier | EntryUsage (graduated vCPU-hour) |
|---|---|
| Price | $0.09 → $0.06 per vCPU-hour (by monthly volume) + $0.09/GiB-mo volume |
| Includes | pure usage, no subscription; pausing a VM stops the meter; machine-readable rate ladder at GET /v1/pricing |
| Storage overage | $0.09/GB |
| vCPU hours overage | $0.09/h |
vCPU-hour (graduated by monthly volume) + volume GiB-month·Card required: unconfirmed·fastvm.org
Overages: vCPU-hour $0.09 → $0.06 graduated by monthly volume; volume storage $0.09/GiB-month; pausing stops the meter
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
VM lifecycle provisioning/running/stopped; pausing a VM stops the meter; state via full-VM snapshots (incl. TCP connections) + managed Volumes (POSIX multi-attach virtio-fs)
Snapshots / forks
Yes
Resources & limits
Storage
diskGiB per VM (overridable at launch); managed Volumes (POSIX-coherent multi-attach via virtio-fs, $0.09/GiB-mo); BYO GCS/S3 bucket mounts; snapshot import from OCI image / Dockerfile
Limits & quotas
org-level quotas: vcpu, memoryMiB, diskGiB, snapshotCount, volumeCount, volumeGiB (limits + usage); 16 services/VM; exec stdout/stderr capped (~4 MiB, truncation flags); default values require auth to query
GPU
No
Access
Deploy interface
sdkapiclissh
SDK languages
PythonTypeScript
Network & secrets
Egress controls
Yes
Secrets
envVars injected at boot (string→string map; ≤256-byte keys, ≤4096-byte values)
Bring your own cloud
No
Placement & use
Jurisdiction
region 'sfo' referenced in benchmarks; no region selection or data-residency disclosed
Advertised workloads
Reinforcement learningAI coding agentsBrowser automationNon deterministic computer use
03 Capabilities 10 pass · 5 partial · 19 fail · 35 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 2/5
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).
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.
Partially 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).
Not assessed
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 assessed
Desktop / computer-use sandboxA virtual desktop (GUI) for LLM computer-use — browser + desktop automation, often via noVNC/VNC.
Not assessed
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 4/6
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 assessed
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 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 assessed
Developer access 4/7
Public APIDocumented programmatic API.
Supported
OpenAPI specMachine-readable OpenAPI / Swagger spec published.
Supported
CLIOfficial command-line tool.
Partially supported
SDKOfficial client library/libraries.
Supported
SSH accessDirect SSH into workloads.
Supported
Filesystem APIRemote file operations over the API (list/read/write/watch/copy/upload) without SSH.
Not assessed
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 assessed
AI & agents 0/6
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 assessed
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 assessed
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 assessed
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 assessed
Platform & operations 0/2
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 assessed
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 assessed
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 0/7
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.
Partially 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 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.
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.
- VMs are IPv6-addressed (publicIpv6, no public IPv4) with a public 4-to-6 HTTP proxy so services stay IPv4-reachabledirect-ipv6
“VM has a publicIpv6 field; services reachable via a public 4to6 HTTP proxy.” fastvm.org
- Snapshot import from a Docker/OCI image or a Dockerfile (build a reusable VM base)sandbox-templates
“/v1/snapshot_imports — import a snapshot from a Docker/OCI image or Dockerfile.” fastvm.org
- BYO GCS/S3 bucket mounts into the VM (object storage as a filesystem)bucket-mounts
“/v1/vms/{id}/bucket-mounts — mount your own GCS/S3 bucket into the VM.” fastvm.org
04 Agent readiness Pre-login surface · counts, not a grade
Can an agent read it?
parse-ability · docs, metadata, machine-readable surfaces
10/11
9 full · 1 partial · 91% of applicable checks
- llms.txtSupported
- llms-full.txtSupported
- robots.txt AI policyPartially supported
- JSON-LDSupported
- SitemapSupported
- Meta tagsSupported
- Markdown negotiationNot supported
- Content efficiencySupported
- Docs discoverableSupported
- Machine-readable pricingSupported
- No anti-bot wallSupported
Can an agent drive it?
act-ability · APIs, SDKs, MCP, credentials, webhooks
7/11
5 full · 2 partial · 64% of applicable checks
- Public APISupported
- OpenAPI specSupported
- MCP serverNot supported
- SDK packagesSupported
- Auth documentedSupported
- Self-serve credentialsPartially supported
- WebhooksNot supported
- CLI toolPartially supported
- Error modelSupported
- Rate limits documentedNot supported
- Agent config filesNot supported
05 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 15
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- Claude Code
- Codex CLI
Devin
Droid- Gemini CLI
Goose
Hermes Agent
Kilo Code
Kiro CLI- OpenCode
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.
Only region 'sfo' (San Francisco) appears — in the boot-time benchmark — not as a selectable placement. No region matrix or data-residency disclosed → disclosed:false.
07 Company & presence Facts only, not scored
Company
- Headquarters
- Unknown
- Founded
- Unknown (live API + SDKs + benchmark labeled May 2026)
- Team size
- Unknown — opaque; no team page
- Hiring
- Unknown (no careers page)
Activity
- Last release
- Python SDK fastvm v0.7.0 (PyPI); benchmark labeled May 2026; sitemap lastmod 2026-06-03; no changelog/release page pypi.org
- Last blog post
- Blog exists but is empty ('Writing coming soon. First posts shortly.') fastvm.org
Presence 4
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 fastvm.org's unauthenticated pages, docs, pricing and repository on 5 Jun 2026. Nothing behind a login was used.
Statuses, not scores
Capabilities are pass, partial or fail against a written rubric (features v3). “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
- v3
- Keys tracked today
- 61
- Assessed on this entry
- 35
Something wrong on this page?
Nearby in the atlas
All Sandbox products →
Agent SafehouseSandbox · Not disclosedOpen source tool
Agent SandboxSandbox · Kata / gVisorOpen source tool
Agent SubstrateSandbox · Kata / gVisorOpen source tool
Agent37Sandbox · Kata / gVisorHosted
AgentNestSandbox · ContainerOpen source tool
Anthropic Sandbox Runtime (srt)Sandbox · ContainerOpen source tool