Code & AI agent sandboxes: read the guide

vmsan

Open source toolSandbox

Firecracker made simple. Spin up secure microVMs in milliseconds, from install to interactive shell in one command — full lifecycle management, network isolation, Docker image support, and shell access (no SSH).

Homepage Docs Repository

Scanned 15 Oct 2026 · Schema v5 · features v21

Licence: Apache-2.0
Self-hosted; you pay for the infrastructure.
Free tier: Free to run
Isolation: Firecracker microVM
shares only the hypervisor
Regions: —
Not disclosed on the public surface.
Capabilities: 9 / 61
2 partial · 27 fail · 0 not assessed
Agent readiness: 10/10 · 4/8
read · drive, pre-login surface

Advertised for

AI agent sandboxing · Untrusted code execution · Multi tenant isolation · Ephemeral microvm sandboxes · CI isolation

Built for

Developers, then technical

· CLI-first (`vmsan create --runtime node22 --memory 512 --cpus 2`); one-command installer
· Deep systems vocabulary: Firecracker, jailer, seccomp, cgroups, KVM, nftables, TAP /30, microVM
· npm + TypeScript library; `--json` output for scripting/automation; Linux + root + KVM prerequisites

01 Website design Desktop public website · assessed 15 Oct 2026

Complete assessment.

Restrained white technical site: large text-led hero and terminal install card, followed by structured three-column documentation with green navigation accents.

Editorial minimalism

Landing page: captured
Pricing: not applicable
Docs: captured

02 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

VMs persist across stop/start (state files in ~/.vmsan/vms/, per-VM ext4 rootfs); snapshots save/restore VM state. Sandbox-oriented (ephemeral by intent) but stoppable/restartable.

Snapshots / forks

Yes

Resources & limits

Storage

Per-VM ext4 rootfs + ~/.vmsan/ state (vms/, rootfs/, snapshots/, registry/ OCI cache); file upload/download over the agent HTTP API (no SSH).

Limits & quotas

Per-VM CPU/memory at create (`--cpus`, `--memory`); per-VM bandwidth cap (`--bandwidth`); bounded by the host machine; single-host (no multi-host until 0.7.0).

GPU

Access

Deploy interface

clisdkcontainer-image

SDK languages

TypeScript

Network & secrets

Egress controls

Yes

Secrets

Bring your own cloud

Placement & use

Jurisdiction

Advertised workloads

AI agent sandboxingUntrusted code executionMulti tenant isolationEphemeral microvm sandboxesCI isolation

03 Capabilities 9 pass · 2 partial · 27 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 4/10

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.

Not supported

GPU computeGPU-backed instances available.

Not supported

Multi-regionCompute placeable in more than one geographic region.

Not applicable

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 1/3

Automatic HTTPSTLS endpoints provisioned automatically per workload.

Not applicable

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

Not supported

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

Not applicable

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

Not applicable

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

Not applicable

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.

Not applicable

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 3/8

Public APIDocumented programmatic API.

Partially supported

OpenAPI specMachine-readable OpenAPI / Swagger spec published.

Not supported

CLIOfficial command-line tool.

Supported

SDKOfficial client library/libraries.

Supported

SSH accessDirect SSH into workloads.

Not 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 applicable

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 applicable

AI & agents 0/9

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 applicable

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 applicable

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 0/1

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 0/3

Scheduled tasksCron / scheduled job primitive.

Not supported

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 applicable

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 1/4

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

Not applicable

SSO / SAMLEnterprise single sign-on.

Not applicable

Secrets managementFirst-class secrets storage / injection.

Partially supported

TeamsMulti-user team accounts.

Not applicable

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

Not applicable

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 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.

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-less shell via WebSocket PTY (interactive shell + exec backed by an in-VM agent HTTP API, no SSH server)websocket-pty-shell
“'run commands, transfer files — no SSH required'; 'Interactive shell — WebSocket PTY with full terminal support'. A Go agent inside the VM exposes an HTTP API for exec/files/shell; the CLI talks to it over the host-guest network.” github.com

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

Can an agent read it?

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

10/10

7 full · 3 partial · 100% of applicable checks

llms.txt
Supported
“Real /llms.txt (1.7KB): summary + links to all docs pages + a llms-full.txt pointer — well-structured.”
llms-full.txt
Supported
“/llms-full.txt present and comprehensive (34KB — the full docs corpus).”
robots.txt AI policy
Partially supported
“robots.txt is default-allow (Allow: / for *) + a Sitemap pointer, with no explicit AI-UA mention (silent default-allow).”
JSON-LD
Partially supported
“1 application/ld+json block, but minimal (@type WebSite only — not SoftwareApplication/Product).”
Sitemap
Supported
“Real /sitemap.xml with 10 URLs (all docs pages + home), referenced from robots.txt.”
Meta tags
Supported
“Complete: descriptive <title>, a real meta description, and full OG set (image×4 + site/title/description/type).”
Markdown negotiation
Supported
“Content negotiation serves clean text/markdown: curl to vmsan.dev returns markdown (not HTML), and /raw/*.md returns text/markdown (e.g. /raw/getting-started/introduction.md → 200 text/markdown).”
Content efficiency
Partially supported
“Fresh browser DOM: 2974 readable text bytes / 83115 HTML bytes = 3.58%, partial (1–5% band).”
Docs discoverable
Supported
“First-class docs site at vmsan.dev (Introduction/Guide/API), linked from the README and llms.txt.”
Machine-readable pricing
Not applicable
“oss-tool — free under Apache-2.0; no hosted pricing surface.”
No anti-bot wall
Supported
“Fresh anonymous Chromium landing/docs and curl documentation/well-known fetches showed no challenge.”

Can an agent drive it?

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

4/8

1 full · 3 partial · 50% of applicable checks

Public API
Partially supported
“A programmatic TypeScript library (npm `vmsan`) + the in-VM agent HTTP API — but a local/library API, not a hosted remote public API.”
OpenAPI spec
Not supported
“No OpenAPI for vmsan's own API (src/generated/ is Firecracker's types).”
MCP server
Not supported
“No MCP server advertised in refreshed full documentation and README.”
SDK packages
Partially supported
“One official SDK (TypeScript, npm `vmsan`); single language → half.”
Auth documented
Not applicable
“Local CLI; no remote API to authenticate to.”
Self-serve credentials
Not applicable
“No hosted signup — self-hosted CLI; nothing to self-serve credentials for.”
Webhooks
Not supported
“No webhooks.”
CLI tool
Supported
“The `vmsan` CLI IS the product — comprehensive, official, with `--json` output for automation.”
Error model
Partially supported
“A typed error system (src/errors/) + `--json` structured output; no separately-documented API JSON error-model spec.”
Rate limits documented
Not applicable
“Local CLI — no hosted API rate limits.”
Agent config files
Not supported
“No agent configuration/skills surface linked from refreshed README or full documentation.”

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 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.

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 —

No region list captured.

07 Open source Apache-2.0 · fetched by machine, not quoted from marketing

Licence & repository

Licence: Apache-2.0OSI
Primary language: TypeScript
Stars: 87
Forks: 8
Created: 28 Feb 2026
Archived: No

Activity

Last commit: 25 Mar 2026
Latest release: v0.3.0 · 14 Mar 2026
Issues open / closed: 5 / 5 · 50% closed

Fresh gh GraphQL: latest v0.3.0 on March 14; repository last pushed March 25. Unarchived, runnable instructions remain public; no later release observed.

Fetched via gh on 15 Oct 2026.

Self-hosting

Methods: binarypackage-managersource-build
You operate: docker

Apache-2.0; self-host is the only mode (no hosted tier). Install via `curl -fsSL https://vmsan.dev/install | bash` → installs into ~/.vmsan/ (bundles Firecracker + Jailer, a vmlinux 6.1 kernel, an Ubuntu 24.04 ext4 rootfs, the CLI + in-VM Go agent, and prebuilt runtimes downloaded from artifacts.vmsan.dev). Also published on npm (`vmsan`) as a CLI + TypeScript library. REQUIRES Linux (x86_64/aarch64) with KVM + root/sudo (TAP networking + jailer); Docker is needed ONLY for `--from-image` and source installs. Single-host (no multi-host until 0.7.0); Linux-only; primary platform Ubuntu 24.04 LTS. Cost = free under Apache-2.0 + your own Linux box with KVM.

Documentation signals 7/8

SupportedQuickstart
SupportedAPI reference
SupportedSelf-host guide
SupportedChangelog
Not supportedOpenAPI
Supportedllms.txt
SupportedExamples
SupportedArchitecture doc

08 Company & presence Facts only, not scored

Company

Headquarters: Not disclosed
Founded: vmsan repo created 2026-02-28
Team size: Single maintainer (@angelorc) + community contributors
Hiring: n/a — community OSS project

Notable people

@angelorc (creator/maintainer)

Activity

Last release: v0.3.0 (2026-03-14) — snapshots; quiet since (pushedAt 2026-03-25) github.com
Last blog post: —

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 vmsan.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 Sandbox products →