Overview
How Msty Claw works and where to start
Msty Claw is Msty's desktop agent app for reliable, end-to-end execution across chat, automation, memory, and operational workflows. You can run local-first, connect cloud providers when needed, and expand into channels and tooling as your workflows mature.
If you are new, start with Setup. If you are deploying Claw in shared or production contexts, apply Security controls before enabling external routing.
Install and compatibility
Download from msty.ai/claw.
Compatible platforms:
- macOS
- Windows
- Linux
What Claw is built for
- Local-first execution with optional cloud-connected workflows
- Bot-based operations with explicit runtime and permission controls
- Durable context through Working Brief and Memory Bank
- Repeatable execution through Playbooks, Tasks, and Shortcuts
- Extensibility through built-in tools and MCP servers
Core product model
Think of Claw as five connected layers:
- Bots: execution identity (workspace, runtime, routing, permissions)
- Memory: live state (Working Brief) plus durable memory packs
- Playbooks and Tasks: reusable and scheduled automation
- Providers and Tools: model routing, MCP capabilities, and search/tooling
- Security and Settings: sender policy, folder/network controls, and app defaults
How to use this documentation
If you are setting up Claw for the first time
- Follow Setup
- Apply Security baseline controls
- Create and test your first Bot
- Add Tools and optional Model Providers
If you are rolling Claw out to a team
- Standardize Working Styles
- Define guardrails in Security
- Package repeatable operations in Playbooks
- Add automation through Tasks
- Add remote routing in Channels only when needed
If you are optimizing day-2 operations
- Improve context durability in Memory Bank
- Reduce repetitive prompting with Shortcuts
- Tune integrations in Managed Services and Tools
- Finalize device/state strategy in Cloud Sync