tools
Browserbase
Browserbase provides cloud browsers, web search, fetching, and runtime tools for building and operating AI agents.
In inglese
Browserbase gives developers browser sessions that AI agents can use to navigate websites, log in, interact with dynamic pages, and perform tasks. It also provides Search and Fetch APIs, agent runtime features, session observability, and model access through Stagehand.
Teams use it for browser automation, web research, monitoring, testing, and workflows that require websites without reliable APIs. The service is cloud-first and does not offer on-premises deployment. Paid plans include usage allowances, with additional browser hours, API calls, proxies, and model usage billed separately.
Features
- Run cloud browser sessions that agents can use to navigate and interact with websites
- Search the web with ranked, token-optimized results through the Search API
- Fetch web pages as HTML, JSON, or Markdown
- Deploy and run agents with Browserbase Functions
- Support logins, dynamic content, CAPTCHA solving, and persistent sessions
- Inspect sessions with recordings, replays, downloads, and dashboard observability
- Use Model Gateway for model access through Stagehand and unified billing
- Run managed browser agents from natural-language goals with one API call
Use cases
- Automate workflows across websites that do not provide usable APIs
- Research the web and return structured context to an AI agent
- Monitor prices, listings, search trends, and competitor changes
- Test customer-facing web flows continuously and detect breakages
- Fill out applications, forms, and vendor or government portals
- Run browser agents across many sites without maintaining separate scripts
Pros
Cons
Latest updates
- Pause & Resume Agent Runs
Agents can now pause mid-run for human-in-the-loop steps, then resume in the same session.
- Webhooks in Functions
Webhooks are now available for Browserbase Functions. Subscribe to events like Function pending, running, completed, and failed.
- Search is in the dashboard
Search is natively in our dashboard, allowing you to sample queries before taking them to production.
- Configurable caching in Stagehand (v4)
Stagehand v4 caches act(), observe(), and extract() results on Browserbase's servers. Now you control it.
- Name your Contexts and manage them in the Dashboard
You can now assign human-readable names your Contexts, and view all previously created Contexts in the dashboard.
Capabilities
- Command line — “Browse CLI Give your agent browsing skills with a single command” source
- Choice of models — “Models Use any model with a single API key” source
- Not: Self-hosted — “While we don't offer on-prem deployment, our cloud infrastructure provides:” source
- API — “Browserbase makes the web as reliable and programmable as APIs” source
- Official SDKs — “Stagehand, the AI SDK for browser agents, is created and maintained by Browserbase.” source
- Runs models for you — “Model Gateway: your Browserbase API key gives access to major models via Stagehand and unified billing.” source
- Builds agents and workflows — “Browserbase is the complete platform to build and deploy agents that browse and interact with the web like humans:” source
- Traces and evaluates — “Observability Unified debugging your agent across replays, logs, and prompts” source
Get it
Security
Pricing
- Starting price
- $20/mo
- Prices checked
- 2026-09-25
Free Plan
Free
- 3 concurrent browsers
- 1 browser hour
- 3 Agent runs included
- 1,000 Search calls
- 1,000 Fetch calls
- 15 minutes /session
Developer Plan
- $20/mo
- 25 concurrent browsers
- 100 browser hours
- 15 Agent runs included
- 1,000 Search calls
- 1,000 Fetch calls
- 1 GB of proxies
Startup Plan
- $99/mo
- 100 concurrent browsers
- 500 browser hours
- 50 Agent runs included
- 1,000 Search calls
- 10,000 Fetch calls
- 5 GB of proxies
Scale Plan
Price on request
- 250+ concurrent browsers
- 500+ browser hours
- Custom Agent runs
- 10,000+ Search calls
- 10,000+ Fetch calls
- HIPAA (BAA) & DPA; SSO available