Code & AI agent sandboxes: read the guide

Browserbase

HostedSandbox

Give your agents access to the whole web.

Homepage Docs Pricing Repository

Scanned 14 Oct 2026 · Schema v5 · features v21

From: $20/mo
Monthly plan plus browser-hour, agent-run, Search/Fetch calls, proxy GB and upstream LLM token usage
Free tier: Yes
No card required.
Isolation: Virtual machine
hypervisor, or nothing at all
Regions: 4
Oregon · Virginia · Frankfurt · Singapore
Capabilities: 14 / 61
5 partial · 30 fail · 0 not assessed
Agent readiness: 11/11 · 11/11
read · drive, pre-login surface

Advertised for

Browser agents · Web scraping · Data extraction · Form automation · Browser testing · Portal automation

Built for

Developers, then technical

· Official API, Node.js/Python SDKs, Browse CLI and coding-harness Skills: https://docs.browserbase.com/welcome/quickstarts/skills
· Browser-hour/API-call metering: https://www.browserbase.com/pricing

01 Pricing Monthly plan plus browser-hour, agent-run, Search/Fetch calls, proxy GB and upstream LLM token usage

Tier	EntryFree	Developer	Startup	TopScale
Price	$0/mo	$20/mo	$99/mo	custom

browser-hour + agent-run + API calls per 1k + proxy GB + model tokens·Card required: No·browserbase.com

Overages: Browser-hour Developer $0.12, Startup $0.10; Search per 1k Parallel Fast $1 / Advanced $5 / Exa $7; Fetch $1 Developer or $0.50 Startup, $4 with Proxies or Extract, $7 with both; proxy rates shown in plan expansion; model tokens market price.

02 Website design Desktop public website · assessed 14 Oct 2026

Complete assessment.

A restrained grid-led desktop site combines orange branding and bold sans-serif hierarchy with recurring dithered landscape imagery. Pricing is a four-column comparison; docs reuse the landscape motif inside a navigation-led layout.

Swiss-inspired
Retro-computing

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

Virtual machinehypervisor, or nothing at all

Persistence

Ephemeral browser VMs; reusable cookies/auth/application-data Contexts; recordings retained 7/30/30+ days by plan

Snapshots / forks

Resources & limits

Storage

Browser recordings/downloads/context state; Function /tmp limited to 512 MB and not isolated or unique per invocation

Limits & quotas

Browser concurrency 3/25/100/250+; hours 1/100/500/custom; 1-minute session minimum; Free 15 min/session. Functions TypeScript only, us-west-2, 60–900 seconds, 512 MB /tmp; Search 2 RPS and Fetch 5 RPS per project.

GPU

Access

Deploy interface

apisdkclimcpdashboard

SDK languages

TypeScriptPython

Network & secrets

Egress controls

Experimental top-frame domain navigation allowlist plus configurable proxies; not a complete outbound firewall

Secrets

Yes

Bring your own cloud

Placement & use

Jurisdiction

US OregonUS VirginiaGermany FrankfurtSingapore

Advertised workloads

Browser agentsWeb scrapingData extractionForm automationBrowser testingPortal automation

04 Capabilities 14 pass · 5 partial · 30 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 2/10

Persistent diskStorage that survives restart/stop (not ephemeral-only).

Not 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).

Not 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.

Supported

Sandbox templates / custom imagesBuild reusable sandbox/VM images from an OCI image or Dockerfile (a base you fork instances from).

Not 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 applicable

Desktop / computer-use sandboxA virtual desktop (GUI) for LLM computer-use — browser + desktop automation, often via noVNC/VNC.

Partially 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 0/3

Automatic HTTPSTLS endpoints provisioned automatically per workload.

Not applicable

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

Not applicable

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).

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.

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 applicable

Developer access 4/8

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.

Not supported

Filesystem APIRemote file operations over the API (list/read/write/watch/copy/upload) without SSH.

Partially supported

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

Not supported

Private container registryHosted private image registry.

Not applicable

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 4/12

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.

Not supported

MCP serverExposes a Model Context Protocol server for agents.

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).

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).

Not supported

Data 0/2

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 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 applicable

Platform & operations 2/5

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 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).

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).

Supported

Organisation & security 2/9

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

Not supported

SSO / SAMLEnterprise single sign-on.

Partially supported

Secrets managementFirst-class secrets storage / injection.

Supported

TeamsMulti-user team accounts.

Supported

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

Not 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).

Partially 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.

Headless browser fleetheadless-browser-fleet
“Create, control, and observe browser sessions programmatically.” docs.browserbase.com
Agent Identity: CAPTCHA solving and stealthagent-identity-stealth
“Browserbase can solve supported CAPTCHA challenges automatically so your sessions can continue.” docs.browserbase.com
Web Fetch and Search APIsweb-fetch-search-api
“Retrieve page content as clean markdown through a proxy network.” docs.browserbase.com
Managed browser-task agentmanaged-browser-agent
“Run autonomous browser agents on Browserbase with one API call.” docs.browserbase.com

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

Can an agent read it?

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

11/11

8 full · 3 partial · 100% of applicable checks

llms.txt
Supported
“https://docs.browserbase.com/llms.txt — HTTP 200, substantive complete documentation index”
llms-full.txt
Supported
“https://docs.browserbase.com/llms-full.txt — HTTP 200, 1117675 bytes, retained capped pointer”
robots.txt AI policy
Partially supported
“https://www.browserbase.com/robots.txt — User-agent: * Allow: /; default allow, no explicit AI user agents”
JSON-LD
Partially supported
“https://www.browserbase.com/ — Organization structured data, not a SoftwareApplication/Product offer model”
Sitemap
Supported
“https://www.browserbase.com/sitemap.xml — HTTP 200, 62090 bytes, nontrivial URL set”
Meta tags
Supported
“https://www.browserbase.com/ — descriptive title/description and OpenGraph in current HTML”
Markdown negotiation
Supported
“https://www.browserbase.com/ and https://docs.browserbase.com/welcome/introduction — Accept: text/markdown returns text/markdown”
Content efficiency
Partially supported
“https://www.browserbase.com/ — HTMLParser visible text 5983 bytes / 380293 HTML bytes = 1.57%”
Docs discoverable
Supported
“https://www.browserbase.com/ — first-class Docs header link”
Machine-readable pricing
Supported
“https://www.browserbase.com/pricing — four structured plans plus comparison rates”
No anti-bot wall
Supported
“Current landing/pricing/docs and well-known files fetched without bot challenges; missing paths are ordinary error pages”

Can an agent drive it?

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

11/11

9 full · 2 partial · 100% of applicable checks

Public API
Supported
“https://docs.browserbase.com/reference/api/openapi.v1.yaml — documented public REST API”
OpenAPI spec
Supported
“https://docs.browserbase.com/reference/api/openapi.v1.yaml — 160403 bytes, OpenAPI 3.0.0”
MCP server
Supported
“https://docs.browserbase.com/integrations/mcp/setup — hosted Streamable HTTP endpoint and local STDIO setup”
SDK packages
Supported
“https://docs.browserbase.com/reference/sdk/overview — official Node.js and Python SDKs”
Auth documented
Supported
“https://docs.browserbase.com/reference/api/create-a-session — x-bb-api-key documented”
Self-serve credentials
Partially supported
“https://docs.browserbase.com/integrations/mcp/setup — obtain API key in dashboard; no programmatic issuance documented”
Webhooks
Supported
“https://docs.browserbase.com/platform/webhooks/verifying-deliveries — signed events and verification”
CLI tool
Supported
“https://docs.browserbase.com/integrations/skills/browse-cli — official Browse CLI”
Error model
Supported
“https://docs.browserbase.com/reference/api/openapi.v1.yaml — structured statusCode/error/message responses”
Rate limits documented
Supported
“https://docs.browserbase.com/optimizations/concurrency/overview — x-ratelimit-limit, remaining, reset, retry-after headers”
Agent config files
Partially supported
“https://docs.browserbase.com/welcome/quickstarts/skills — documented installable Skills surface; agents.md/well-known agent endpoint not found”

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

Advertised integrations 3

Claude Code Anthropic
Supported
“Browserbase Skills teach AI coding agents (like Claude Code, Cursor, and Codex) how to browse and interact with the web”
Source docs.browserbase.com
Cursor Anysphere
Supported
“Browserbase Skills teach AI coding agents (like Claude Code, Cursor, and Codex) how to browse and interact with the web”
Source docs.browserbase.com
Codex CLI OpenAI
Supported
“Browserbase Skills teach AI coding agents (like Claude Code, Cursor, and Codex) how to browse and interact with the web”
Source docs.browserbase.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
certifiedhosted
“SOC 2 Type 2 Report - 2026”
Source trust.browserbase.com
HIPAA
enterprise-onlyhosted
“HIPAA compliant: Business Associate Agreements (BAAs) available”
Source docs.browserbase.com
SOC 2 Type I
certifiedhosted
“SOC 2 Type 1”
Source trust.browserbase.com

Regions 4

Oregonus-west-2
Virginiaus-east-1
Frankfurteu-central-1
Singaporeap-southeast-1

Current specific browser region reference supersedes broad pricing FAQ regions. Functions only us-west-2.

Legal

Privacy notice Terms of service

08 Company & presence Facts only, not scored

Company

Headquarters: San Francisco, California, US
Founded: —
Team size: Not disclosed
Hiring: Open roles

Activity

Last release: 2026-10-14 — Parallel is now available in Browserbase Search browserbase.com
Last blog post: 2026-10-14 browserbase.com

Presence 6

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 browserbase.com'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 →