madcop
Run multi-model agent workflows, tools, MCP servers, and local knowledge from one desktop app.
- Stars
- 102
- Forks
- 4
- Updated
- Updated Jul 14, 2026
Run multi-model agent workflows, tools, MCP servers, and local knowledge from one desktop app.
MadCop is a cross-platform, local-first desktop workstation for multi-step AI work. It connects to a user-supplied OpenAI-compatible endpoint and combines persistent conversations, files, a local knowledge base, built-in tools, MCP servers, and several workflow modes in one workspace. Conversations, files, and knowledge are stored locally, while remote-model requests are sent directly to the endpoint the user configures. The documented setup is primarily source-based rather than a hosted account service.
Resource types
Use cases
Operating systems
Organize files, write documents, and automate browser tasks from a local desktop agent.
Set up and operate OpenClaw agents without using a terminal.
Runtime
Protocols & integrations
Capabilities
Public GitHub facts last synced Jul 14, 2026.
Automate Windows applications and websites with visual RPA workflows.
Automate work across desktop chat, messaging apps, and hundreds of SaaS integrations.