Code & AI agent sandboxes: read the guide

E2B

Open coreSandbox

Every agent gets a machine

Homepage Docs Pricing Repository

Scanned 14 Oct 2026 · Schema v5 · features v21

From: $150/mo
Monthly plan plus per-second vCPU and RAM usage
Free tier: Yes
No card required.
Isolation: Firecracker microVM
shares only the hypervisor
Regions: 4
US, GCP, all plans default · US West, AWS, all plans via support · EU, GCP, Pro+ via support · APAC, GCP, Pro+ via support
Capabilities: 27 / 61
5 partial · 27 fail · 0 not assessed
Agent readiness: 10/11 · 10/11
read · drive, pre-login surface

Advertised for

Agent code execution · Coding agents · Computer use · Data analysis · MCP hosting

Built for

Developers, then technical

· Python/JavaScript SDK and API-driven Linux microVM lifecycle
· Custom templates, CLI and OpenAPI

01 Pricing Monthly plan plus per-second vCPU and RAM usage

Tier	EntryHobby	Pro	TopEnterprise
Price	Free + usage	$150/mo + usage	Custom; $3,000 monthly usage minimum
Includes	$100 one-time usage credit · 1h max session · 20 concurrent sandboxes · 10 GiB free storage · community support · no CC	everything in Hobby · custom Sandbox CPU/RAM · 24h max session · 100 concurrent (purchasable to 1,100) · 20 GiB free storage	Negotiated limits, managed BYOC, support and billing
Storage	10 GB	20 GB	—
Storage overage	$0/GB	$0/GB	—
Compute hours overage	$0.0504/h	$0.0504/h	—

vCPU-second + GiB-RAM-second; sandbox storage included·Card required: No·$0.000014/vCPU-second + $0.0000045/GiB-second; storage free·e2b.dev

02 Website design Desktop public website · assessed 14 Oct 2026

Complete assessment.

Black-and-white technical website with orange-red accents, monospaced utility labels and large display typography. Landing uses a pixel-field fleet illustration; pricing uses a strict card grid; docs use a three-column code-oriented layout.

Swiss-inspired
Retro-computing
Technical illustration

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

Firecracker microVMshares only the hypervisor

Persistence

Disk and memory preserved by pause/resume; paused retention unlimited

Snapshots / forks

Snapshots and live sandbox fork supported

Resources & limits

Storage

10 GiB Hobby / 20+ GiB Pro sandbox disk included; independent volumes in private beta

Limits & quotas

Hobby 20 concurrency / 1h; Pro 100–1100 / 24h; paused retention unlimited

GPU

Access

Deploy interface

sdkcliapi

SDK languages

PythonJavaScriptTypeScript

Network & secrets

Egress controls

Per-sandbox IP/CIDR/domain allow and deny; disable internet; external secret injection

Secrets

Write-only secrets resolved in outbound HTTPS proxy outside guest; workload identity private beta

Bring your own cloud

Managed Enterprise data plane in AWS, GCP or Azure customer VPC

Placement & use

Jurisdiction

FoundryLabs, Inc., Delaware; managed regions US/EU/APAC

Advertised workloads

Agent code executionCoding agentsComputer useData analysisMCP hosting

04 Capabilities 27 pass · 5 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 7/11

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.

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.

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.

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.

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).

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 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 7/10

Public APIDocumented programmatic API.

Supported

OpenAPI specMachine-readable OpenAPI / Swagger spec published.

Supported

CLIOfficial command-line tool.

Supported

SDKOfficial client library/libraries.

Supported

SSH accessDirect SSH into workloads.

Partially 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.

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).

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 3/11

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.

Partially 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).

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 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).

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 1/5

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 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 5/9

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).

Partially supported

BYOCRuns inside the customer's own cloud account.

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).

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).

Partially supported

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

Supported

05 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 · 2 partial · 91% of applicable checks

llms.txt
Supported
“https://docs.e2b.dev/llms.txt; 38091-byte rich index captured.”
llms-full.txt
Supported
“https://docs.e2b.dev/llms-full.txt; 1476923 bytes, retained pointer plus scored modular documents.”
robots.txt AI policy
Supported
“Fresh robots.txt explicitly allows GPTBot, ClaudeBot, Google-Extended and other AI UAs.”
JSON-LD
Partially supported
“Homepage Organization JSON-LD with legal name/contact/social links; no Product offer structure.”
Sitemap
Supported
“Fresh sitemap.xml 18987 bytes; nontrivial URL set.”
Meta tags
Supported
“Descriptive title, meta description and Open Graph title/description in raw HTML.”
Markdown negotiation
Supported
“Official .md representations served as clean Markdown; pricing, enterprise, security and docs pages retained.”
Content efficiency
Partially supported
“14849 readable bytes / 755054 HTML bytes = 1.97%; stdlib HTML parser excluding scripts/styles.”
Docs discoverable
Supported
“DOCS in top-level rendered header links.”
Machine-readable pricing
Supported
“pricing.md enumerates plans, usage rates and concurrency add-ons in tables.”
No anti-bot wall
Supported
“Landing, pricing, docs and trust public pages fetched without challenge.”

Can an agent drive it?

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

10/11

9 full · 2 partial · 91% of applicable checks

Public API
Supported
“API reference and OpenAPI in fresh docs index.”
OpenAPI spec
Supported
“https://docs.e2b.dev/openapi-public.yaml returned 200, 475236 bytes.”
MCP server
Supported
“Installable official e2b-dev/mcp-server documented; deprecated maintenance caveat retained, no assertion of successful live use.”
SDK packages
Supported
“Official Python and JavaScript SDK install instructions and fresh releases.”
Auth documented
Supported
“docs.e2b.dev/api-key.md documents E2B_API_KEY and key management.”
Self-serve credentials
Partially supported
“Human browser signup and dashboard key acquisition explicitly required by pricing.md setup guide.”
Webhooks
Supported
“sandbox/lifecycle-events-webhooks.md documents events and signing.”
CLI tool
Supported
“Official @e2b/cli fresh release metadata.”
Error model
Supported
“Fresh OpenAPI spec declares response and error structures.”
Rate limits documented
Supported
“billing.md gives per-project per-endpoint limits and 429 Retry-After behavior.”
Agent config files
Partially supported
“Official https://e2b.dev/SKILL.md; .well-known/agent.json returned 404. llms files are documentation discovery, not extra agent config.”

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

Advertised integrations 3

Claude Code Anthropic
Supported
“Coding agents like Claude Code, Codex, and Amp can write, debug, and refactor code autonomously.”
Source docs.e2b.dev
Codex CLI OpenAI
Supported
“Coding agents like Claude Code, Codex, and Amp can write, debug, and refactor code autonomously.”
Source docs.e2b.dev
Amp Sourcegraph
Supported
“Coding agents like Claude Code, Codex, and Amp can write, debug, and refactor code autonomously.”
Source docs.e2b.dev

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 2

SOC 2 Type II
certifiedhostedPublic explicit vendor claim; report NDA-gated, not independently audited here.
“E2B maintains a SOC 2 Type II report.”
Source e2b.devConfidence: high
HIPAA
enterprise-onlyhosted
“E2B signs HIPAA Business Associate Agreements on Enterprise plans.”
Source e2b.devConfidence: high

Regions 4

US, GCP, all plans defaultus-west1
US West, AWS, all plans via supportus-west-2
EU, GCP, Pro+ via supporteurope-west1
APAC, GCP, Pro+ via supportasia-southeast1

More specific FAQ enumerates AWS US West although security/enterprise summary says Google Cloud. No static egress IPs on any plan.

Legal

Privacy notice Terms of service

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

Licence & repository

Licence: Apache-2.0OSI
Primary language: Python
Stars: 14,353
Forks: 1,112
Created: 4 Mar 2023
Archived: No

Activity

Last commit: 14 Oct 2026
Latest release: @e2b/[email protected] · 13 Oct 2026
Issues open / closed: 34 / 370 · 92% closed

Eight monorepo package releases on 2026-10-13; package-specific tags, not a single server version.

Fetched via gh on 14 Oct 2026.

Self-hosting

Methods: composeterraformkubernetessource-build
You operate: postgresredisobject-storageclickhouse

Apache-2.0 plus your infrastructure costs. Embed runs the full stack on one Linux x86-64 KVM host; Compose, Terraform and Kubernetes packaging. PostgreSQL, Redis, ClickHouse and object storage in the stack. Single-node Embed is not the managed fleet; managed BYOC is separate.

Documentation signals 8/8

SupportedQuickstart
SupportedAPI reference
SupportedSelf-host guide
SupportedChangelog
SupportedOpenAPI
Supportedllms.txt
SupportedExamples
SupportedArchitecture doc

09 Company & presence Facts only, not scored

Company

Headquarters: San Francisco and Prague
Founded: 2023
Team size: Not disclosed
Hiring: Hiring

Notable people

Vasek Mlejnsky
Tomas Valenta

Activity

Last release: 2026-10-13 SDK/CLI monorepo package releases github.com
Last blog post: Blog reachable; exact most recent publication date not established e2b.dev

Presence 5

Links found on the public surface scanned; not an exhaustive search.

10 Sources & method How this entry was produced

Public surface only

Everything here was read from e2b.dev's unauthenticated pages, docs, pricing and repository on 14 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 →