Skip to content

AgentAnthropic

Claude Cowork

Claude Code's agentic harness, repointed at non-coding knowledge work.

Category
Agent
Pricing
PAID
Source
Proprietary
Hosting
Local
Platforms
macOSWindows
Models
Single model (proprietary)
Verified
Jun 12, 2026

Anthropic's agentic desktop mode that completes multi-step knowledge work end-to-end. Point it at local folders and connected apps and it organizes files, builds spreadsheets, and prepares reports — showing its plan for approval before significant actions. Launched as a research preview in January 2026, it is now included in every paid Claude plan on macOS and Windows.

Capabilities 5

What it actually does — grouped by capability family.

  • Trigger-action automation (primary capability)
  • Browser automation (secondary capability)
  • Spreadsheet automation (primary capability)
  • Document parsing (structured) (secondary capability)
  • Report generation (primary capability)

Pros & cons

  • Completes multi-step file tasks end-to-end
  • Scoped folder access with plan approval
  • Bundled into existing paid Claude plans
  • Slack, Chrome, and Zoom connectors
  • Desktop-only — no web or mobile version
  • Requires a paid Claude plan
  • Anthropic models only
  • Long agentic runs can burn plan usage limits

Tags

Further reading

Alternatives to Claude Cowork (3)

View all Agent →
  • View Manus details
    AgentFREEMIUM

    Manus

    Meta (formerly Monica / Manus AI)

    General-purpose autonomous agent for research, ops, and content.

    Cloud agent that browses, drafts, schedules, and follows multi-step instructions over hours. Closer to a virtual operator than a coding tool — strong for non-code knowledge work. Acquired by Meta; product continues to ship.

    Runs tasks autonomously over hours
    Credits drain fast on complex tasks
    • autonomous
    • general-purpose
    • ops
    • browser
    Open
  • View Genspark details
    AgentFREEMIUM

    Genspark

    MainFunc

    All-in-one AI workspace with an autonomous Super Agent.

    An AI workspace built around a Super Agent that breaks goals into sub-tasks, picks the right tools, and finishes work autonomously — building slides, sheets, docs, websites, and videos, and even placing phone calls. It orchestrates multiple large language models and dozens of integrated tools, synthesizing results into shareable Sparkpages. Built by a team from Google and Microsoft and available on web and mobile.

    Autonomous multi-step Super Agent
    Quality uneven across task types
    • super-agent
    • autonomous
    • workspace
    • research
    Open
  • View OpenClaw details
    AssistantBYO KEYOSS

    OpenClaw

    OpenClaw Foundation

    Local-first personal AI assistant you run on your own devices, on any platform.

    A self-hosted, local-first personal AI assistant with a gateway as the control plane, reachable across messaging channels like WhatsApp, Telegram, Slack, and Discord. It runs on macOS, Linux, Windows, iOS, and Android, with an onboarding wizard for setup. Free and open source under MIT; you supply your own model API key.

    Free to self-host on your own devices
    Self-host setup required
    • personal-assistant
    • local-first
    • self-hosted
    • open-source
    • +1
    Open
Open Claude Cowork