---
title: Personal AI agents
tags:
  - wiki
  - concepts
sources:
  - "[[A sane but extremely bull case on OpenClaw (Clawdbot)]]"
  - "[[OpenClaw Our Comprehensive Guide for Beginners]]"
  - "[[OpenClaw Security 101 The Complete Guide]]"
  - "[[OpenClaw, OpenAI and the future]]"
  - "[[Introducing Moltworker a self-hosted personal AI agent, minus the minis]]"
  - "[[Moltbook is the most interesting place on the internet right now]]"
  - "[[Introducing Eve]]"
  - "[[Omniagent - a meta-harness for building and running AI agents]]"
  - "[[Build Your First AI Agent in Just 5 Minutes!]]"
  - "[[Promoting AI agents]]"
date: "2026-07-17T06:24:18.965Z"
created: "2026-07-17T06:24:18.965Z"
includeInRss: false
---

# Personal AI agents

Always-on / messaging-native agents (OpenClaw lineage, Eve, Moltworker, meta-harnesses) vs session-bound IDE agents.

## Takeaways

- Persistence + tools + identity/memory beats chatbox demos.
- **Security isolation is table stakes** — separate machine/VM, allowlists, Docker subagents, Tailscale.
- Skills marketplaces create leverage and supply-chain risk.
- Folder-as-agent (Eve) and meta-harness (Omnigent) are competing packaging models.
- “Promoting agents” (DHH-ish): supervised terminal agents > in-editor autocomplete cosplay.

## Open questions

- Where OpenClaw-style agents end and this vault’s Cursor skills begin (overlap vs complement)?
- Foundation/governance after big-lab hires.