Stagehand
Open-source TypeScript framework for browser automation, maintained by Browserbase. Hybrid of Playwright-style imperative APIs and AI-driven natural-language actions (e.g. page.act('click the sign-up button')). Used as the OSS substrate that Browserbase Cloud composes with.
At a glance
- Type
- OSS browser-automation framework (Browserbase OSS)
- Tier
- T1
- Section
- Computer-use & desktop agents
- Created
- 2024 (Browserbase release)
- Latest release
- v2.x; active monthly releases (npm: @browserbasehq/stagehand)
- License
- MIT
- Pricing
- OSS free; Browserbase Cloud handles runtime
- Funding
- Maintained by Browserbase ($40M Series B Q4 2024; Kleiner Perkins)
Taxonomy
- storage
- file
- retrieval
- injection
- persistence
- session
- update
- agent-controlled
- unit
- document
- governance
- inspectable
- conflict
- human-arbitrate
When to use
Optimised for: Playwright-replacement with AI verbs (act / extract / observe)
Anti-fit: TS-only; not a finished agent — caller wires logic; tied closely to Browserbase ecosystem
Pros & cons
Pros
Browserbase-backed OSS; clean act/extract/observe primitive; growing TS-agent ecosystem.
Cons
TS-only (no Python parity); ties best with Browserbase Cloud (vendor adjacency).
Claims & capabilities
Maintained by Browserbase Inc.; 9k+ GH stars; AI + deterministic hybrid
Technical surface
- API surface
- TS API (act/extract/observe); npm: @browserbasehq/stagehand
- Backend storage
- Local Playwright state; Browserbase-managed when cloud-hosted
- Deployment
- Library — runs anywhere Playwright runs; Browserbase Cloud for managed
- Embedding model
- not applicable — not a memory product
- Multi-tenancy
- Per-process in OSS; per-tenant in Browserbase Cloud
- MCP
- Composes with Browserbase MCP server
- A2A
- searched not found
- OpenTelemetry
- searched not found
Compare Stagehand with…
Similar systems
Other computer-use & desktop agents in the catalog, ranked by inbound references.
- UI-TARS T2
ByteDance Seed's open-source GUI-agent foundation model — released Jan 2025; trained end-to-end on screenshot → action pairs. Comes with UI-TARS-Desktop (Electron app) that runs the model against the user's screen. SOTA on OSWorld at release; weights on HuggingFace.
- Browser Use T1
Python library that turns any LLM into a browser agent — extracts DOM into a structured representation the LLM can act on (rather than pure screenshot). Browser Use Inc. raised $17M seed Q1 2025 (Felicis); cloud product at cloud.browser-use.com. Project is one of the most-starred browser-agent OSS repos (~60k stars).
- Bytebot T3
Open-source desktop-agent runtime that runs an LLM-controlled Linux desktop inside Docker — uses xdotool / X11 capture for control. Pitched as the 'self-hosted Operator' alternative; agent sees a real desktop screen, not just a browser.
- Claude for Chrome T1
Anthropic's Chrome extension that lets Claude act inside the user's existing browser (rather than a sandboxed one). Research preview launched August 2025 — limited to Claude Max tier. Distinct from Anthropic Computer Use (which is the API substrate); this is the consumer surface that uses it inside Chrome.
- Highlight AI T2
Always-on desktop AI assistant that watches the user's screen (across all apps) and answers questions / takes actions based on what's currently visible. Mac + Windows. Founded by Mac Bishop (ex-Mixpanel); raised $13M Series A from Aspect / Lightspeed (Oct 2024). Distinguishes itself from Rewind by being action-oriented (not just recall).
- Hyperbrowser T2
Cloud-hosted headless browser API tuned for AI agents — captcha solving, stealth mode, session recordings. Y Combinator S24; pitched as a faster / cheaper Browserbase alternative. Used as substrate by agents that need browser execution but don't want to run their own Chromium fleet.