Hyperbrowser
Also known as: Hyperbrowser AI
Cloud browser infrastructure for AI agents: stealth browser sessions in five regions, web scraping and extraction APIs, hosted computer-use agents, and sandboxes.
Hyperbrowser, built by S2 Labs, is cloud infrastructure for AI agents on the web. Its browser sessions run in a choice of five regions (three in the US, one in western Europe, one in south Asia), connect to Playwright, Puppeteer or Selenium, and come with stealth, residential proxies, CAPTCHA solving, profiles, extensions, rrweb and MP4 recordings, and a live view a person can watch or take over. Credential fill types stored logins and one time codes into login forms without the customer's code or a model seeing them, and a 1Password integration feeds sandboxes and browsers.
Web APIs fetch, search, scrape, crawl and extract structured data from pages. Hosted agent tasks run HyperAgent, Browser Use or computer-use agents from Anthropic, OpenAI, Google, Meta, xAI and Jev with one API call, and the open source HyperAgent framework adds page.ai() actions, multiple LLM providers and action caching that replays recorded steps without model calls. Hyperbrowser also sells sandboxes, including GPU sandboxes, with memory snapshots, volumes, custom images and a CLI, for running agents in harnessed cloud environments.
Pricing is credit based at a tenth of a cent per credit. A free plan comes with 5,000 credits, Startup is $30 a month with 30,000 credits, Scale is $100 a month with 100,000, and Enterprise is custom, with 1,000 or more concurrent browsers and longer data retention. Browser time runs $0.10 an hour, proxy data $10 per GB, a scraped page a tenth of a cent, and a sandbox $0.045 per vCPU hour plus $0.015 per GiB hour of memory. Hyperbrowser's Security Commitments describe controls aligned with SOC 2 criteria, encryption and annual penetration testing. Customer accounts have no SSO or roles.
Vendor details
Canonical URL
https://www.hyperbrowser.ai
Category
Agent infrastructure
Subcategory
Browser infrastructure
Funding status
Independent, Y Combinator backed, founded 2021 in San Francisco, with Accel and SV Angel among investors. The hosted cloud platform is proprietary, while the HyperAgent framework, MCP server, and Python and Node SDKs are open source under the MIT license.
Company status
independent
Use cases & customers
Primary use cases
Target customers
Deployment options
Integrations
REST API with Python (hyperbrowser) and Node.js (@hyperbrowser/sdk) SDKs, the hx CLI for sandboxes, and an open source MCP server; Playwright, Puppeteer and Selenium connections; LangChain, LlamaIndex, Stagehand, AI function calling and x402 integrations; hosted HyperAgent, Browser Use and computer-use agents from Anthropic, OpenAI, Google, Meta, xAI and Jev.
In practice
Your agent gets blocked by bot walls on the sites it needs. Hyperbrowser's cloud browser sessions come with stealth, proxies and CAPTCHA solving, so the agent reaches the site reliably.
You want an agent to browse using natural language, not selectors. HyperAgent, the open source framework, adds page.ai() actions, so you describe the task and the agent works through its steps across pages, with custom actions for your own tools.
You need browser sessions at scale without maintaining a grid. Hyperbrowser starts a managed cloud browser session with one API call, in the region you choose, and records every session so you can replay what the agent did.
Sources & related URLs
Agentic Index coverage score
8.0 / 14 capabilities · 57%
| Integrations & Tool Calling | Full |
|---|---|
|
LangChain, LlamaIndex, Stagehand and AI function calling guides give an agent Hyperbrowser's browser, scrape and crawl as tools. HyperAgent's custom actions let a developer add their own tools, and x402 lets agents pay for fetches and searches. Credential fill types stored logins and one time codes into a site's login form without the customer's code or a model seeing the values, and a 1Password integration reads fields into sandbox processes and browser logins, so agents can act inside signed in accounts. Sourcehyperbrowser.ai/docs/integrations/langchainread 2026-11-03 |
|
| Workflow Orchestration | Partial |
|
One API call starts a hosted HyperAgent, Browser Use or model native computer use task (Claude, OpenAI, Gemini, Meta, Grok, Jev) in a managed session. The agent works through its steps, and the customer polls status, reads results or stops it. The open source HyperAgent adds multi page management within one agent. Each task is one agent working through a multi step loop. Hyperbrowser has no workflow composition, step chaining or multi agent execution of its own, and action caching replays one agent's steps. Sourcehyperbrowser.ai/docs/agents/overviewread 2026-11-03 |
|
| Knowledge Grounding & RAG | Not documented |
|
Fetch, search, scrape, crawl and AI extract endpoints turn public web pages into markdown, HTML or structured data for the customer's own pipeline. Hyperbrowser keeps no index, vector store or grounding layer of its own over customer content. Sourcehyperbrowser.ai/docs/web/overviewread 2026-11-03 |
|
| Human Oversight & Guardrails | Partial |
|
Every session carries a Live View URL that the customer can embed in its own application. Through it a person can watch and interact with the running browser, and human in the loop interactions are one of its named uses. There is no approval gate, pause primitive or policy guardrail, and the customer's code decides when to hand control to a person. Sourcehyperbrowser.ai/docs/sessions/live-viewread 2026-11-03 |
|
| Security, Identity & Governance | Partial |
|
The information security program is aligned with the SOC 2 Trust Services Criteria. It covers independent third party assessments, annual third party penetration testing, encryption at rest and in transit, vulnerability scanning, logging and monitoring, incident response, and backup and recovery. The Enterprise plan lists 'HIPAA/SOC 2', but the Security Commitments say only 'aligned with', so the attestation is unclear. Access controls (least privilege, quarterly access reviews, SSO where available) govern Hyperbrowser's own team. Customer accounts have no SSO, roles or permissions. Sourcehyperbrowser.ai/securityread 2026-11-03 |
|
| Observability & Auditability | Partial |
|
Every session is recorded. Web recordings (rrweb) capture DOM changes, interactions and network requests for replay, and MP4 video recordings are available too. Both are fetched through the API, and every session has a live view. Data retention runs by plan, with 7 days on Free, 30 on Startup and Scale, and 180 or more on Enterprise. A customer can replay what the agent did in the browser. There is no structured log of each agent action, no audit log separate from the recording and no export to a monitoring system. Sourcehyperbrowser.ai/docs/sessions/recordingsread 2026-11-03 |
|
| Memory & State Persistence | Partial |
|
Sandboxes carry state forward. A memory snapshot freezes a running sandbox's memory, processes and filesystem, and new sandboxes start from that state. Volumes persist data across sandboxes, so the agent's own code reads the restored state to carry on. A snapshot restores the machine's state whole, and volumes are storage the code reads. There is no separate memory layer with its own scope and lifetime. Browser profiles hold the saved login loaded at session start, and HyperAgent action caching replays recorded actions without LLM calls. Sourcehyperbrowser.ai/docs/sandboxes/snapshotsread 2026-11-03 |
|
| Deployment & Data Residency | Full |
|
Customers choose a region for each browser session from a published list of us-central, us-east, us-west, europe-west and asia-south. Production data is hosted in United States databases unless otherwise agreed in writing. There is no self hosted option. Sourcehyperbrowser.ai/docs/sessions/regionsread 2026-11-03 |
|
| Prebuilt Agents, Templates & Packs | Partial |
|
A templates gallery offers ready to run sample projects built on the Hyperbrowser APIs, such as a news sentiment aggregator, product review analyzer, shopping recommenders, and API servers wrapping Hacker News, Product Hunt and Craigslist, among others. An examples repository sits alongside. A developer clones and adapts these projects, and there is no catalog of agents a customer adopts as they are. Sourcehyperbrowser.ai/templatesread 2026-11-03 |
|
| Triggers & Channel Coverage | Not documented |
|
Work starts when a caller creates a session, sandbox, scrape job or agent task through the API or SDKs. No event, schedule, webhook or inbound queue of Hyperbrowser's own starts agent work. Scheduled jobs are a listed use case for action caching replays, but the customer runs the schedule. Sourcehyperbrowser.ai/docs/api-reference/create-new-sessionread 2026-11-03 |
|
| Model Flexibility & Routing | Full |
|
The customer chooses the model behind the hosted agents. Each task starts with a chosen agent, either HyperAgent, Browser Use or a model native computer use agent from Anthropic (Claude), OpenAI (CUA), Google (Gemini), Meta, xAI (Grok) or Jev. Each is billed by its own model's tokens or steps, and HyperAgent supports OpenAI, Anthropic and Google Gemini models as configured providers. Sourcehyperbrowser.ai/docs/agents/overviewread 2026-11-03 |
|
| APIs, SDKs & MCP Extensibility | Full |
|
A REST API makes the platform callable from outside, covering sessions, profiles, extensions, sandboxes, volumes, snapshots, fetch, search, scrape, crawl, extract and agent tasks, with a full API reference. Official Python (pip install hyperbrowser) and Node.js (@hyperbrowser/sdk) SDKs sit alongside it, with the hx CLI for sandboxes and an open source MCP server. Sourcehyperbrowser.ai/docs/sdks/introductionread 2026-11-03 |
|
| Testing, Debugging & Optimization | Not documented |
|
Agents run on the platform, but it does not score them. There are no fixtures, scoring, quality gates or comparison of agent runs. Session recordings and live view serve for debugging, and action caching replays recorded actions deterministically to cut cost. Sourcehyperbrowser.ai/docs/introductionread 2026-11-03 |
|
| Browser & Computer Use | Full |
|
The product is a real cloud browser that agents operate. Agents drive cloud browser sessions through Playwright, Puppeteer or Selenium, use computer actions (click, type, scroll, screenshot), or run as hosted computer use agents from Anthropic, OpenAI, Google, Meta, xAI and Jev. Stealth, proxies, CAPTCHA solving, profiles and extensions support production use. Sourcehyperbrowser.ai/docs/introductionread 2026-11-03 |
|
The Agentic Index coverage score grades every vendor Full, Partial or Not documented against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded
Product updates
Browser sessions on Hyperbrowser can now discover and call WebMCP tools that a website registers in its pages, instead of clicking through the interface. Agents call those tools like functions with a description and an input schema, and a form that needs a person to submit it waits in the session until a human finishes it through Live View. Support ships in the Node.js SDK 1.2.0, the Python SDK 1.11.0 and the REST API.
Bears on: MCP / tool calling / API
View sourcePricing
Free 5,000 credits · Startup $30/mo plus usage · browser hours $0.10
Credits at $0.001 each, drawn by browser hours, proxy data, web API pages and queries, AI extract tokens, agent steps or model tokens, and sandbox vCPU and memory hours; plan credits refresh on renewal, purchased credits expire after 12 months
Included quota
Free tier includes 1,000 credits and 1 concurrent browser with no card. Usage draws credits at 1 credit ($0.001) each, with a browser hour costing about 100 credits ($0.10) and a scraped page 1 credit. Subscription plans refresh credits on renewal; directly purchased credits expire after 12 months.
What is public
Per credit, per browser hour and per page rates, the free tier and the Startup and Scale subscriptions are published; Enterprise is custom.
Billing mechanics
Credit based, where 1 credit is $0.001. Browser sessions consume about 100 credits per browser hour and scrapes 1 credit per page. Credits come from subscription plans (refresh on renewal) or direct purchase (expire in 12 months).
Cost watchouts
Proxy data at $10 per GB usually outweighs browser hours, and hosted computer-use agents bill their own model tokens on top of browser time; credits bought outside a subscription expire after 12 months.
Variable cost rationale
Every service draws credits by use (browser hours, proxy data, pages, extraction tokens, agent steps and model tokens), so concurrency, proxy needs and agent choice drive nearly all cost above the plan's included credits.
Overage / add-ons
Usage draws down credits at published rates (about 100 credits per browser hour, 1 per scraped page); subscription credits refresh on renewal, purchased credits expire after 12 months.
Sales call required
Mixed (some tiers require a call)
Free / trial
Free plan with 5,000 credits; a 14-day trial on Enterprise plans
Lowest paid plan
Startup $30 a month plus usage
Commercial notes
Independent, Y Combinator backed, founded 2021, with Accel and SV Angel among investors. Cloud platform proprietary; HyperAgent, MCP server, and SDKs open source under MIT.
Key ambiguities
Total cost mixes browser hours, proxy data, per-page web API calls, extraction tokens and agent steps or model tokens, so the plan's included credits cover different amounts of work depending on the mix.
Related vendors
- AgentOps — Agent observability and debugging platform: open source SDKs trace…
- AgentPhone — AgentPhone gives the AI agents a team builds their own US or…
- Agno — Python agent framework and AgentOS runtime (formerly Phidata) for…
- AIsa — Resource and payment gateway for AI agents, with one key to 110+…
- Albato — Albato is a no code integration platform that sells an embedded,…
- AlphaBitCore — AI control plane for regulated financial firms: one gateway enforces…
Alternatives to Hyperbrowser
The closest documented capability profiles to Hyperbrowser among agent infrastructure platforms tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.
- E2B8.0 / 14Adds documented Triggers & Channel Coverage
- Lightpanda6.0 / 14A lighter documented profile than Hyperbrowser
- Deepgram7.5 / 14Adds documented Triggers & Channel Coverage
- AIsa6.0 / 14Fuller documented coverage on Prebuilt Agents, Templates & Packs
- Daytona8.0 / 14Adds documented Triggers & Channel Coverage
- Modal8.0 / 14Adds documented Triggers & Channel Coverage
Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded