Browserless

The AI integrations section gives agents a Browserless browser inside Browser Use, Stagehand, LangChain, the Claude Agent SDK, Claude Code, Hermes Agent, AgentKit and computer-use agents from Anthropic, OpenAI and Gemini, plus n8n, Make and Zapier. Authenticated profiles and a 1Password integration resolve credentials into sessions for logged-in action on outside sites.

Sourcedocs.browserless.io/ai-integrations/startread 2026-09-23

Browserless executes multi-step browser sequences of its own: BrowserQL scripts chain navigation, waits, conditional logic and structured extraction in one request, and the Agent Run API (beta) runs a managed agent that plans and executes its own browser steps asynchronously, bounded by maxSteps. Both are one browser or one agent's loop. No workflow composition across steps or agents, and no multi-participant execution, is documented.

Sourcedocs.browserless.io/browserql/startread 2026-09-23

No index, vector store or grounding layer over the customer's own content is documented. Browserless's smart scrape, search, map and crawl tools turn public web pages into structured, LLM-ready output for the customer's own pipeline, but extraction and search over the public web is not a retrieval structure the vendor maintains over the customer's corpus.

Sourcedocs.browserless.io/rest-apis/smart-scraperead 2026-09-23

A person can take over mid-run, and the managed agent works inside set limits. Hybrid automation pauses an automated script, hands control to a person through a secure live URL (interactive or view-only), and resumes the automation when they finish, for logins, 2FA, CAPTCHAs or any step that needs human judgment. The Agent Run API constrains a managed agent with a navigation allowlist (allowedDomains) and a step cap (maxSteps), which are policy guardrails on what the agent may do.

Sourcedocs.browserless.io/baas/monitor-sessions/hybrid-automationread 2026-09-23

Attested and access-controlled, both on Browserless's own pages.

On compliance, the Trust Center (updated 11 September 2026) lists SOC 2 Type II, GDPR compliance, a BAA for Enterprise and a DPA for deployments Browserless operates, and states the SOC 2 scope: organization-wide controls, with infrastructure-hosting controls scoped to its cloud, and a self-hosted deployment inside the customer's own audit boundary.

On access, the pricing page lists SSO and user roles on Enterprise, and the self-hosted page documents role-based access with per-team tokens in admin, developer, viewer and public roles.

Sourcebrowserless.io/trustread 2026-09-23

The agent's actions are recorded and kept by plan. Session Replay captures each session as an interactive replay in the dashboard (DOM mutations, mouse movements, clicks, scrolling, keyboard input and console output), request logs are searchable in the dashboard, and each poll of an Agent Run returns the steps the agent has taken with short rationales.

The 1Password integration keeps an audit log of every credential resolve (reference, origin and outcome, never the value). Retention runs by plan: replay storage from 1 day on Free to 90 days on Scale and custom on Enterprise, and a log search window from 8 hours to 7 days.

Sourcedocs.browserless.io/baas/monitor-sessions/session-replayread 2026-09-23

What persists is browser state, and no agent memory with a stated scope and lifetime is documented. Persisted sessions keep cookies, cache and local storage between sessions, authenticated profiles store logins by name, reconnects keep a browser warm so an automation picks up where it left off, and the MCP browser agent holds one browser session across tool calls. Each is browser state loaded or kept for the next connection rather than a memory the agent reads to decide, so it is a setting, part of what makes the hosted browser production grade.

Sourcedocs.browserless.io/baas/session-management/persisting-stateread 2026-09-23

Customers choose between their own environment and a list of cloud regions. The self-hosted page runs the same APIs inside the customer's own VPC, on premises or on an air-gapped network, with an enterprise Docker and Kubernetes deployment guide and air-gapped licensing. The pricing page lists San Francisco, London and Amsterdam cloud endpoints on every plan, and Enterprise adds private deployments, custom datacenter locations and extensive locations including the EU. Either route gives a buyer a choice of where the browsers run.

Sourcebrowserless.io/platform/self-hostedread 2026-09-23

A browsable catalog of units that do work when selected ships as the Agent Skill Catalog, which lists 136 production-tested skills across 123 sites and 14 categories (real estate, ecommerce, finance, government, jobs and others). Each is a whole task, such as searching AbeBooks by ISBN and extracting sorted results or finding recent electrical building permits, versioned, listed automatically and callable through the Browserless MCP with structured JSON output.

Sourcebrowserless.io/skillsread 2026-09-23

Browserless starts work when a caller connects over WebSocket or calls a REST, BrowserQL, MCP or Agent Run endpoint; no event, schedule or inbound channel of its own starts agent work. Agent Run's webhooks are outbound notifications that a run finished, and the scheduled examples run on Zapier's scheduler. The broad protocol coverage is how callers reach Browserless, not what starts it.

Sourcedocs.browserless.io/overview/connection-urlsread 2026-09-23

The one model Browserless runs, behind the Agent Run API (beta), is fully managed: the docs say the customer supplies no model key, and no model or provider selection is documented. Everywhere else the model lives in the customer's own agent (Browser Use, Stagehand, LangChain, computer-use agents), and choosing which assistant calls Browserless is not the same as choosing a model inside it.

Sourcedocs.browserless.io/rest-apis/agent-runread 2026-09-23

Browserless is callable from outside through documented interfaces: REST APIs with a published OpenAPI specification, BrowserQL (a GraphQL-based automation language with an editor), Browsers as a Service over WebSocket for Puppeteer, Playwright and Selenium, the Agent Run API, a CLI, and a hosted MCP server with scrape, search, map, crawl, function and agent tools.

Sourcedocs.browserless.io/open-apiread 2026-09-23

No fixtures, scoring, quality gates or comparison of agent runs are documented as Browserless features. The MCP server's performance tool runs Lighthouse audits that score web pages, not the customer's agent workflows, and Session Replay and hybrid automation are recording and takeover tools rather than evaluation.

Sourcedocs.browserless.io/mcp/browserless-mcp-serverread 2026-09-23

Operating a real browser for agents is Browserless's product: managed Chrome, Firefox and WebKit that an agent drives through Puppeteer, Playwright, Selenium, BrowserQL, the MCP browser agent or computer-use agents from Anthropic, OpenAI and Gemini, with stealth, residential proxies, automatic CAPTCHA solving and Chrome extensions for production use.

Sourcebrowserless.ioread 2026-09-23