Anchor Browser vs Browserbase (2026)

Managed authentication and authenticated applications give agents logged in sessions on outside sites, with MFA, email one time codes and a 1Password integration for credentials. Named integrations connect Anchor to automation tools (n8n, Make, Zapier), agent and browser frameworks (CrewAI, LangChain, Stagehand, Browser Use) and sandboxes (Daytona, CreateOS, Tenki).

Sourcedocs.anchorbrowser.io/essentials/authenticated-applicationsread 2026-09-23

Browserbase Agents have four built in tool groups (browser, search, shell and files) and cannot take custom tools yet. The integrations directory (Stripe cards, 1Password logins, Box, n8n and agent frameworks) connects services to sessions that the customer's own code drives.

Sourcedocs.browserbase.com/platform/agents/how-it-worksread 2026-09-27

Automation Tasks are versioned workflows of ordered segments that mix deterministic Playwright code with agentic steps, and they run in Anchor's own runtime. Anchor launches the browser, authenticates, and walks each segment in order, with a workflow graph showing step status. Runs can be synchronous or asynchronous, whole runs retry on a new browser, and a single step can fall back to an AI agent mid-run.

Sourcedocs.anchorbrowser.io/tasks/overviewread 2026-09-23

An Agent run plans and executes multi step browser work, reusable Agents run one prompt across many inputs, and Functions host the customer's own scripts behind an API. Sequencing, branching and retries across runs live in the customer's code, and there is no workflow model.

Sourcedocs.browserbase.com/platform/functions/overviewread 2026-09-27

Anchor describes Automation Tasks as versioned, repeatable workflows with managed identities, scheduling and session control, but no schedule setting is offered. Runs start with an API call (POST /v2/tasks/{taskId}/run), task settings cover identity, human-in-the-loop, retries and browser configuration with no schedule among them, and webhooks send outbound event notifications instead of starting runs.

Sourcedocs.anchorbrowser.io/introductionread 2026-09-23

Runs and Functions start from the API, SDKs, the Browse CLI or the MCP server. To run a Function on a cron, the customer uses its own webhook, queue worker or scheduled job. Browserbase's webhooks are outbound notices, and Browserbase runs no schedule itself.

Sourcedocs.browserbase.com/platform/webhooks/overviewread 2026-09-27

Anchor keeps no knowledge base or retrieval layer over the customer's own content, and has no index, vector store or grounding layer of its own. Its agents and tools read and extract content from live web pages through research tasks, screenshots and file downloads for the customer's own use, which is extraction from the public web, not search over the customer's documents.

Sourcedocs.anchorbrowser.io/examples/research-taskread 2026-09-23

There is no retrieval over the customer's own knowledge. Search and Fetch read the public web at run time.

Sourcedocs.browserbase.com/llms.txtread 2026-09-27

The agent has no memory of its own with a set scope and lifetime. Between runs, Anchor keeps the browser's state. Managed authentication keeps agents signed in to outside applications through encrypted, session-based authentication, and browser profiles carry a stable identity, including a dedicated sticky IP, across sessions. The browser loads each of these at session start, so they work like a saved browser login, not as context the agent reads to decide.

Sourcedocs.anchorbrowser.io/essentials/managed-authenticationread 2026-09-23

An Agent reads its memory of earlier steps within a run. Contexts keep cookies, local storage and cache across sessions, but that is saved browser state, and the Agent has no memory store it reads across runs.

Sourcedocs.browserbase.com/platform/browser/core-features/contextsread 2026-09-27

With human in the loop enabled, the agent pauses and posts an intervention request to a session-specific queue. The customer lists pending requests and sends a response through API endpoints, or subscribes to the intervention.requested webhook, whose payload carries the request ID, the agent's message and a live-view URL for one-click takeover. Automation Task settings switch human-in-the-loop on per task, so a person can review and direct the agent mid-run.

Sourcedocs.anchorbrowser.io/agentic-browser-control/human-in-the-loopread 2026-09-23

A run given pauseWhen pauses when the stated condition arises, such as an approval or a verification code. It tells the customer what it needs and continues where it left off once they reply. Allowed Domains limits where sessions may browse.

Sourcedocs.browserbase.com/platform/agents/pausing-runsread 2026-09-27

SOC 2 Type 2, ISO 27001 and GDPR come from the Growth plan, with a BAA, HIPAA and a DPA on Enterprise, and a trust portal holds the compliance report. SSO and RBAC are on Enterprise, and user roles are part of the account configuration Anchor keeps. Each browser runs in a dedicated virtual machine that is destroyed at session end, with strict tenant isolation, encrypted session-based authentication, and a Zero Data Retention mode that turns off all video and log recording for an account.

Sourcedocs.anchorbrowser.io/securityread 2026-09-23

Organizations assign Admin, Contributor and Viewer roles, and the Scale plan adds SAML single sign on. Every plan has SOC 2 Type II, and HIPAA with a BAA, a DPA and third party penetration tests are available, with a trust center at trust.browserbase.com.

Sourcedocs.browserbase.com/account/enterprise/securityread 2026-09-27

An Automation Task run shows a steps panel that streams per-segment logs with timestamps, an Agent Logs section wherever an AI agent completed a step, and a workflow graph marking each segment's status. The Runs tab keeps every past execution, and View run replays it against the session recording. Sessions are recorded to MP4 by default and served through the API and web UI, console logs can be turned on, and a session history endpoint lists past sessions. Retention is configurable down to a Zero Data Retention mode.

Sourcedocs.anchorbrowser.io/essentials/recordingread 2026-09-23

Each Agent run keeps a chronological message transcript of what the Agent did. Every session has live view, session replay and downloadable recordings. Logs are kept for 7 to 30 or more days depending on plan, and logging can be turned off.

Sourcedocs.browserbase.com/platform/browser/observability/observabilityread 2026-09-27

Region choice depends on the plan. Free and Starter run in the US, Growth adds the EU, Asia and Australia, and Enterprise can use any region. By default, infrastructure is hosted in the United States, with customer data processed and stored in AWS us-east-2 (Ohio), and EU-based infrastructure is available for organizations that need it.

Sourcedocs.anchorbrowser.io/pricingread 2026-09-23

The Sessions API takes a region parameter, and data residency is configurable across US, EU and Asia regions. Enterprise accounts get zero data retention and bring your own storage. The service is hosted only.

Sourcedocs.browserbase.com/optimizations/latency/multi-regionread 2026-09-27

Starting points come in two forms. Task examples cover form filling, buyer intent, configuration collection and research, and a library of guides shows how to automate named business applications such as NetSuite, SAP S/4HANA, Salesforce and ServiceNow, and US federal forms such as IRS Form W-7, Form I-9 and VA Form 21-526EZ, with Playwright. Each guide is a set of setup steps and a script that a developer adapts, examples to build from, not a catalog of agents ready to adopt.

Sourcedocs.anchorbrowser.io/examples/task-examplesread 2026-09-23

The Agents examples are worked task recipes (KYC checks, price monitoring, many portals) that the customer writes into its own Agent, and Skills teach coding agents to use Browserbase. There are no packaged agents or templates to adopt.

Sourcedocs.browserbase.com/platform/agents/examplesread 2026-09-27

Customers choose the model behind Anchor's own agent. Perform-web-task takes an agent parameter, browser-use by default, openai-cua or gemini-computer-use, and AI steps are priced by the tier of the model used. Bring Your Own Keys lets a project store its own provider keys for OpenAI, Anthropic, Google, Azure or any OpenAI-compatible endpoint and opt in per request, and Anchor's default model applies otherwise.

Sourcedocs.anchorbrowser.io/advanced/bring-your-own-keyread 2026-09-23

Model Gateway lets a customer pick OpenAI, Anthropic or Google models by name on a Browserbase API key, and enterprise security includes bring your own LLM. Browserbase Agents themselves take no model setting, and the gateway is used through the Stagehand SDK.

Sourcedocs.browserbase.com/platform/model-gateway/overviewread 2026-09-27

Anchor can be called from outside through a REST API at api.anchorbrowser.io, authenticated by API key, that covers browser sessions, session history, AI tasks, automation tasks, agent access and webhooks. SDKs exist for JavaScript (npm anchorbrowser) and Python, alongside a hosted MCP server for any user with an API key and an open source MCP server.

Sourcedocs.anchorbrowser.io/quickstart/use-via-apiread 2026-09-23

A REST API covers sessions, contexts, Agents, Functions, Fetch and Search, with Node.js and Python SDKs, the Browse CLI and a Browserbase MCP server.

Sourcedocs.browserbase.com/reference/introductionread 2026-09-27

Automation Tasks are versioned, so a draft is test-run with real inputs before it replaces the live version, and every run carries a status and per-step results. Workflow self-healing analyzes a run whose deterministic step failed and creates a new draft version for the customer to review, turning what the agent completed at run time into a stronger workflow. There are no scored test cases.

Sourcedocs.anchorbrowser.io/advanced/self-healingread 2026-09-23

The Optimize tool analyzes completed Agent runs and proposes a system prompt change to run again. Each Agent tracks completion, fail and timeout rates and average duration over its run history, so the deployed Agent can be improved from one run to the next.

Sourcedocs.browserbase.com/platform/agents/optimizing-agentsread 2026-09-27

Running real browsers for agents is the core product. Headful Chromium sessions run in dedicated virtual machines that an agent drives through CDP with Playwright or Puppeteer, through Anchor's own browser agent, or through Anthropic, OpenAI, Gemini and Yutori computer-use agents. Sessions come with OS-level mouse and keyboard control, stealth, proxies, CAPTCHA solving and authenticated sessions.

Sourcedocs.anchorbrowser.io/advanced/os-level-controlread 2026-09-23

Browserbase runs hosted Chromium browsers, one per VM, which agents and Playwright, Puppeteer or Selenium code drive, with stealth, CAPTCHA solving, proxies and live view. Browserbase Agents browse, click, type and extract on the web in their own session.

Sourcedocs.browserbase.com/platform/agents/overviewread 2026-09-27