Scrapybara

Overview

Scrapybara hosts remote desktop instances for computer-use agents. Through the Python or TypeScript SDK (or the REST API) you start an Ubuntu 22.04 desktop, a Browser instance, or a Windows 11 desktop (early access), then drive it with a computer tool for mouse and keyboard actions, a bash tool, a file tool, built-in Jupyter notebooks and a Playwright/CDP browser protocol. An interactive stream URL lets a human watch or take over. The docs provide ready-made tool classes for Anthropic computer use and OpenAI CUA, and an "Act SDK" that runs an agent loop against an instance. The isolation technology is not documented.

Instances stop after a default one-hour timeout unless you set timeout_hours; they can be paused and resumed, and browser auth states can be saved and loaded into later instances. There is no public pricing page: the docs say instances are billed per usage, with Windows at twice the compute cost of Ubuntu. The company homepage now reads "Scrapybara built computers for agents. Now we're building Capy", an AI software-engineering product, while the Scrapybara docs, API reference and SDK repositories remain online with no sunset notice (SDK and MCP repositories were last updated in October 2026).

Notable

• Company homepage (checked 9 November 2026) describes Scrapybara in the past tense and points to its new product, Capy; the Scrapybara docs carry no deprecation notice
• Windows 11 instances are in early access, with slow startup and "2x compute cost" compared with Ubuntu (docs)
• Open-source Python and TypeScript SDKs, an MCP server (MIT) and a CLI on GitHub; the hosted service itself is closed

Scrapybara specifications

Facts from Scrapybara’s public documentation, verified November 9, 2026. Performance numbers are vendor claims.

Strengths and trade-offs

Strengths

• You want Ubuntu, browser and Windows desktops behind one SDK with computer, bash, file and notebook tools built in
• You need pre-built tool definitions for Anthropic computer use or OpenAI CUA
• You want to save browser auth states and reuse logged-in sessions across instances

Trade-offs

• Isolation technology, pricing, regions and compliance are not documented
• The company has publicly moved on to a new product (Capy); long-term support of the Scrapybara API is unclear
• Stopping an instance deletes all data; no snapshot or image feature is documented

Good fit for: Computer-use agents that need a ready-made Ubuntu or Windows desktop with a browser, bash, filesystem and Jupyter tools in one API.

Use cases Scrapybara fits

• Computer use: Ready-made Ubuntu or Windows desktops with browser, bash, filesystem and Jupyter tools in one API; the company has since pivoted to a new product, so check its status.

How Scrapybara compares

See all Scrapybara alternatives →

Frequently asked questions

Sources

1. scrapybara.com
2. docs.scrapybara.com/introduction.md
3. docs.scrapybara.com/quickstart.md
4. docs.scrapybara.com/best-practices.md
5. docs.scrapybara.com/ubuntu.md
6. docs.scrapybara.com/windows.md
7. docs.scrapybara.com/api-reference/start.md
8. docs.scrapybara.com/api-reference/instance/pause.md
9. docs.scrapybara.com/llms.txt
10. github.com/scrapybara
11. capy.ai