Notes on running personal AI agents via Clawdbot. I recently discovered Clawdbot, the general idea of which I had been following since a [tweet](https://x.com/Yampeleg/status/2000642897402880491) from Yam Peleg: ![[Pasted image 20260128192703.png]] That was on December 15, and in late January we've now seen a massive wave of [Clawdbots](https://clawd.bot/) ## What is Clawdbot **Clawdbot** is an AI gateway that bridges messaging platforms (WhatsApp, Telegram, Discord, iMessage) to Claude. You run it on a server, link your messaging accounts, and your AI agent can send/receive messages on your behalf. Think of it as giving Claude a phone number. i.e: An actual SIM card from a real carrier service (in my case, in the Netherlands) ## Architecture ``` WhatsApp ←→ Clawdbot Gateway ←→ Claude API ↓ Agent Workspaces ├── SOUL.md (personality, rules) ├── TOOLS.md (tool instructions) ├── CONTACTS.md (known people) └── memory/ (conversation logs) ``` Each agent has its own workspace with markdown files that define its behavior. The gateway handles message routing, session management, and tool execution. So far, I've set up 2 agents, one for small tests on a VPS, and another as a group experiment with about 45 people as a kind of community co-ordinator. I'll be updating this page with more details when the experiment has run its course, but so far I have over 250 messages sent to the agent (from other than me), and quite a few people have found it helpful. I think we'll see a lot more of this in the future so I am tracking it very closely.