Hyperbrowser
Credit-billed cloud Chrome sessions with profiles, stealth and captcha solving, plus one-shot agent runs (Claude Computer Use, OpenAI CUA, Browser Use) and separate VM-based code sandboxes. A credit-priced browser cloud with the broadest built-in agent-model support, held back by thin isolation and compliance documentation.
Overview
Hyperbrowser is a cloud platform for AI agents from the Y Combinator-backed company of the same name. Its browser product gives you Chrome sessions you drive with Playwright or Puppeteer over CDP from the Node.js or Python SDK, with live view, recordings, profiles, stealth and captcha solving. The docs describe sessions as isolated browser instances but do not name the boundary. An Agents API runs a task to completion with HyperAgent, Browser Use, Claude Computer Use or OpenAI CUA, either blocking or by polling a job.
Everything bills in credits (1,000 per dollar): browsers at $0.10 per hour, proxies at $10/GB and agent steps at $0.02. Per-session timeouts run from 1 to 720 minutes, and keepAlive holds a session across disconnects. A separate Sandboxes product (CPU, GPU and beta macOS) runs code in isolated virtual machines with volumes and custom Docker images, priced per vCPU-hour and GiB-hour; this record covers the browser product. An hyperbrowser-mcp server exposes scrape, extract and crawl tools.
Notable
- Y Combinator company (YC profile lists Summer 2021 batch, founded 2021, team of 4, San Francisco)
- Homepage claims 100M+ browser sessions run and 1,000+ concurrent isolated browsers
- Five regions, with asia-south limited to Enterprise and Select plans
Hyperbrowser specifications
| Attribute | Details |
|---|---|
| Isolation | Sessions are described as isolated browser instances running in the cloud; the boundary is not named. The separate Sandboxes product states commands run in isolated virtual machines |
| Deployment | Hosted platform |
| Open source | No |
| SDKs and interfaces | Python, JavaScript/TypeScript, CLI, REST API, MCP server |
| Cold start (vendor claim) | Homepage claims under 500 ms from request to a ready browser |
| Max session length | Team default timeout (configurable in settings); per-session timeoutMinutes from 1 to 720 (12 hours); keepAlive keeps a session running after CDP disconnect until timeout or stop |
| Persistence | Profiles snapshot the user data directory (cookies, local storage, session storage, cache) and reload it in later sessions; persistChanges controls writes; profiles.fork() copies a profile |
| GPU | No for browsers; GPU (CUDA) sandboxes exist in the separate Sandboxes product |
| Networking | Residential proxies at $10/GB with country/state/city selection or custom proxies; captcha solving; basic and ultra stealth modes |
| Pricing | Credits, 1,000 credits = $1. Browser $0.10/hour, proxy $10/GB, sandboxes $0.045/vCPU-hour + $0.015/GiB-hour, HyperAgent/Browser Use $0.02/step. Free: 5,000 credits, 1 concurrent. Startup $30/month: 30,000 credits, 25 concurrent. Scale $100/month: 100,000 credits, 100 concurrent. Enterprise: custom, 1,000+ concurrent |
| Free tier | Free plan: 5,000 credits (about 50 browser hours at base rate), 1 concurrent session, 7-day retention |
| Compliance | Security programme aligned with SOC 2 Trust Services Criteria with independent assessments; no certification named; production data stored in US cloud databases unless agreed otherwise |
| Regions | us-central, us-east, us-west, europe-west; asia-south on Enterprise/Select plans |
Facts from Hyperbrowser’s public documentation, verified November 9, 2026. Performance numbers are vendor claims.
Strengths and trade-offs
Strengths
- You want low per-hour browser pricing with a usable free tier
- You need to run Claude Computer Use, OpenAI CUA or Browser Use as a hosted task
- You want profiles that persist logins and can be forked
- You need a European or Asian region
Trade-offs
- Isolation boundary for browsers is not documented
- No named compliance certification; only alignment with SOC 2 criteria
- No self-hosting or BYOC
- The MCP server covers scraping and crawling rather than interactive browsing
Good fit for: Agents that need cheap browser hours with a built-in path to run computer-use models as one-shot tasks.
How Hyperbrowser compares
| Sandbox | Isolation | Open source | Self-host / BYOC | Cold start (vendor) | Max session | Snapshots / pause | GPU | SDKs |
|---|---|---|---|---|---|---|---|---|
| Hyperbrowser | Isolated browser instance | No | No / No | <500 ms (claim) | Up to 12 h | No / No | No | Python, JavaScript/TypeScript, CLI, REST API, MCP server |
| Browserbase | Isolated Chromium session | No | No / No | <2 s (claim) | 6 h (15 min Free) | No / No | No | Python, JavaScript/TypeScript, REST API, MCP server |
| Steel | Isolated Chromium session | Yes | Yes / No | Not documented | 15 min / 1 h / 24 h | No / No | No | Python, JavaScript/TypeScript, Go, Rust, CLI, REST API, MCP server |
| Anchor Browser | Dedicated VM per browser | No | No / Yes | Not documented | 3 h default, configurable | No / No | No | Python, JavaScript/TypeScript, REST API, MCP server |
| Browser Use Cloud | Isolated browser per run | No | No / No | Not documented | 1 h default, 4 h max | No / No | No | Python, JavaScript/TypeScript, REST API |
| Kernel | Unikernel VM per browser | Yes | Yes / No | ~30 ms p50 (claim) | Up to 72 h | Yes / Yes | Yes | JavaScript/TypeScript, Python, Go, CLI, REST API, MCP server |
| Notte | Isolated browser instance | Yes | No / No | Not documented | 15 min to 5 h by plan | No / No | No | Python, JavaScript/TypeScript, CLI, REST API, MCP server |
Frequently asked questions
What is Hyperbrowser?
How does Hyperbrowser isolate code?
Is Hyperbrowser open source?
How much does Hyperbrowser cost?
What are the alternatives to Hyperbrowser?
Sources
- hyperbrowser.ai
- hyperbrowser.ai/pricing
- hyperbrowser.ai/security
- hyperbrowser.ai/docs
- hyperbrowser.ai/docs/sessions/overview
- hyperbrowser.ai/docs/sessions/lifecycle.md
- hyperbrowser.ai/docs/sessions/profiles
- hyperbrowser.ai/docs/sessions/regions.md
- hyperbrowser.ai/docs/agents/claude-computer-use.md
- hyperbrowser.ai/docs/sandboxes/introduction.md
- hyperbrowser.ai/docs/integrations/model-context-protocol.md
- ycombinator.com/companies/hyperbrowser
Cite this page
Agent Sandboxes. (2026). Hyperbrowser. agentsandboxes.org. Last reviewed November 9, 2026. https://agentsandboxes.org/sandboxes/hyperbrowser/
Found an error or a missing sandbox? Submit a correction — every entry links to the sources it relies on.