PAI

Add the Cua MCP Server

Connect Claude Code to your Cua sandboxes:

claude mcp add cua-mcp -- cua serve-mcp

Verify the connection:

claude mcp list

Before explaining what Clawdbot is, here’s what people are doing with it:

• $4,200 car discount: AJ Stuyvenberg had his bot orchestrate a bidding war between dealerships. The bot negotiated via text while he watched. Full breakdown here.

• Insurance fight: Someone’s bot accidentally started a dispute with their insurance company, leading to case reinvestigation

• 180 million tokens: Federico Viticci (MacStories) burned through 180M tokens in roughly a week of experimenting

• Nokia development: A user claimed they’re “literally building a whole website on a Nokia 3310” by texting their bot instructions

• Mac Mini phenomenon: Multiple people bought Mac Minis specifically to run it 24/7

Features

• Automatic Classification:Categorizes documents as meetings, ideas, references, journals, or projects

• Entity Extraction: Identifies people, organizations, concepts, and locations

• Daily Summaries: Generates concise summaries of each day's activity (runs at 6 AM UTC)

• Weekly Reports: Creates comprehensive weekly reviews with themes and follow-ups

• Bidirectional Sync: Seamlessly syncs between local vault and AWS S3

• Obsidian Compatible: Works with standard Obsidian vault structure

• Cost Effective: ~$15-20/month for typical usage (50-100 docs/month)

eric's project

To say that Clawdbot has fundamentally altered my perspective of what it means to have an intelligent, personal AI assistant in 2026 would be an understatement. I’ve been playing around with Clawdbot so much, I’ve burned through 180 million tokens on the Anthropic API (yikes), and I’ve had fewer and fewer conversations with the “regular” Claude and ChatGPT apps in the process. Don’t get me wrong: Clawdbot is a nerdy project, a tinkerer’s laboratory that is not poised to overtake the popularity of consumer LLMs any time soon. Still, Clawdbot points at a fascinating future for digital assistants, and it’s exactly the kind of bleeding-edge project that MacStories readers will appreciate.

Clawdbot can be overwhelming at first, so I’ll try my best to explain what it is and why it’s so exciting and fun to play around with. Clawdbot is, at a high level, two things:

• An LLM-powered agent that runs on your computer and can use many of the popular models such as Claude, Gemini, etc.

• A “gateway” that lets you talk to the agent using the messaging app of your choice, including iMessage, Telegram, WhatsApp and others.

The second aspect was immediately fascinating to me: instead of having to install yet another app, Clawdbot’s integration with multiple messaging services meant I could use it in an app I was already familiar with. Plus, having an assistant live in Messages or Telegram further contributes to the feeling that you’re sending requests to an actual assistant.

The “agent” part of Clawdbot is key, however. Clawdbot runs entirely on your computer, locally, and keeps its settings, preferences, user memories, and other instructions as literal folders and Markdown documents on your machine. Think of it as the equivalent of Obsidian: while there is a cloud service behind it (for Obsidian, it’s Sync; for Clawdbot, it’s the LLM provider you choose), everything else runs locally, on-device, and can be directly controlled and infinitely tweaked by you, either manually, or by asking Clawdbot to change a specific aspect of itself to suit your needs.

My local Clawdbot setup. It’s just folders and some Markdown files.