Catalog Systems Computer-use & desktop agents Anthropic Computer Use

Anthropic Computer Use

https://docs.anthropic.com/en/docs/agents-and-tools/computer-use

Anthropic's API-surface capability that lets Claude control a virtual desktop — see screenshots, type, click. Launched 2024-10 as a public beta. Not a finished IDE itself; it's the substrate that other harnesses (and Anthropic's own Claude apps) use to operate a computer.

Active · Verified 2026-10-31 · fresh as of 2026-10-31 · 63 cited facts, 11 with a third-party source · 3 recorded changes · Suggest a correction

At a glance

Type
Claude desktop-control capability (Anthropic API) vendor fix
Tier
T1
Section
Computer-use & desktop agents
Created
2024-10 vendor fix
Latest release
computer_toolset_20260801 (2026-08) — current tool version, no beta header required vendor fix
License
proprietary (Claude API feature) vendor fix
GitHub
not applicable — no GitHub repo fix
Pricing
Standard Claude API token pricing; ~4.5k input-token toolset overhead plus screenshots billed as image input; no per-action fee vendor fix
Funding
Anthropic (parent) — $65B Series H at $965B post-money (2026-05-28); S-1 filed for a proposed IPO (2026-10-26) vendor fix
Freshness
2026-10-31 fix
Layer
agent-infra repo fix
Licensing
commercial vendor fix
Deployment locus
computer-use vendor fix
Platform vs product
platform vendor fix
SDK languages
csharp, go, java, php, python, rest, ruby, typescript vendor fix
Compliance
csa-star, hipaa, iso27001, iso42001, soc2-type2 vendor fix

When to use

Optimised for: Claude controlling a computer screen

Anti-fit: stateless capability — caller manages memory + safety

Pros & cons

Pros

First and most-discussed computer-control LLM; substrate for many higher-level agentic apps; benchmark numbers are public.

Cons

Stateless — every implementer rebuilds the memory + safety layer; per-action API cost is unpredictable.

Claims & capabilities

Anthropic API capability; first computer-control LLM at a major lab; SWE-bench / OSWorld benchmarks shipped with launch.

Technical surface

API surface
Anthropic Messages API with computer-use tool
Backend storage
stateless API
Deployment
Managed-only — Claude API tool (also Bedrock, Vertex, Foundry); actions execute in a caller-provided desktop environment
Embedding model
not applicable — not a memory product
Multi-tenancy
API tenant
MCP
no — computer use is a client-executed API tool, not an MCP server or client
A2A
searched not found
OpenTelemetry
searched not found

Compare Anthropic Computer Use with…

Alternatives to Anthropic Computer Use → live options ranked by shared design, licence, hosting and MCP support

Similar systems

Other computer-use & desktop agents in the catalog, ranked by inbound references.

  • 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.

  • Stagehand T1

    Open-source browser-automation framework by Browserbase (TypeScript core plus Python and Go SDKs). Mixes Playwright-style code with natural-language act/extract/observe; pairs with Browserbase Cloud.

  • 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.

  • 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.

  • Skyvern T2

    Open-source autonomous browser agent that uses computer vision + LLMs to navigate websites. Workflow-based: agents follow recorded plans that adapt to layout changes. Skyvern Inc. raised $4.5M seed (Sep-2024, Felicis lead). Self-hostable; cloud version on skyvern.com.

  • 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.

Sources (62 cited facts, 11 third-party)

Each fact links to the page it came from; the badge says who published it (how to read sources).

What changed

Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)

  1. 2026-11-02
    • License “not applicable — not OSS” → “proprietary (Claude API feature)” source
    #393
  2. 2026-10-28
    • Funding / ownership “Anthropic (parent — $13.7B Sep-2025)” → “Anthropic (parent) — $65B Series H at $965B post-money (2026-05-28); S-1 filed for a proposed IPO (2026-10-26)” source
    #294
  3. 2026-10-26
    • Latest release “not applicable — not OSS” → “computer_toolset_20260801 (2026-08) — current tool version, no beta header required” source
    • Pricing “API per-token + per-screen-action” → “Standard Claude API token pricing; ~4.5k input-token toolset overhead plus screenshots billed as image input; no per-action fee” source
    • Deployment “API (Anthropic Cloud) — runs on caller's machine via local environment” → “Managed-only — Claude API tool (also Bedrock, Vertex, Foundry); actions execute in a caller-provided desktop environment” source
    • MCP support first recorded as “no — computer use is a client-executed API tool, not an MCP server or client” source
    #258

Related systems

References (1)

Referenced by (1)

  • Portkey AI integrates with — Portkey docs have an Anthropic Computer Use app/library integration page. (verified 2026-10-29)