(2026-05-06) Yang The Race To Build A Personal Ai Agentand Why Nobody Has Won Yet

Peter Yang: The Race to Build a Personal AI Agent (And Why Nobody Has Won Yet). Everyone wants an AI chief of staff that can triage emails, book meetings, edit documents, and take care of work that we don’t want to do.

In this post, I'll share:

  • 10 capabilities a great personal agent needs
  • An honest take on where each product stands today
  • The personal agent stack that I use right now

I think a great personal agent needs to be able to:

  • Manage email, calendar, docs, sheets, and slides
  • Integrate with any API, MCP, or CLI
  • Run recurring and triggered tasks
  • Remember things about you
  • Work across web and mobile with no friction
  • Switch between text and voice replies
  • Have a personality that’s fun to talk to
  • Use your computer and browser
  • Stay reliable
  • Keep your data safe

The reality is that no product checks all 10 boxes today. Here’s how each stacks up: Chart

OpenClaw: The most flexible personal agent, but reliability is a real problem

Hermes: I was skeptical at first, but it breaks less often than OpenClaw

It communicates more what it’s doing. It tells me in Telegram when it completes a cron job and how long a task is taking.
It tends to work more independently. When it spots a repetitive workflow, it turns it into a reusable skill automatically. This can be a pro or a con depending on how much control you want to give up.

OpenClaw still feels more “alive” thanks to its transparent heartbeat and memory system, but I’d take reliability over those features any day.

Claude Code: The best personality, but availability and rate limits are a concern

routines, remote control, and chat channels

Claude Code also has major reliability issues:

Mobile integration is manual. You have to type /remote-control to continue your chats on mobile, and it sometimes disconnects after a while.

Codex: An incredible desktop app and generous limits, but no mobile yet

Codex has one big gap: you can’t talk to it on mobile yet

Google Gemini: This is Google’s race to lose

it just doesn’t have all the capabilities yet

But the Gemini app still can’t edit Google Docs, Sheets, or Slides. All of these products are owned by Google, so it’s not great that Gemini is the only AI app that doesn’t support this. Codex and Claude Code do it natively with a few simple connections.

My personal agent stack right now

  • Hermes for everyday tasks.
  • Codex and Claude Code for building things

Once you have an agent that’s available 24/7 and can actually get work done for you, you’ll never go back to a regular AI chat interface again.

My personal agent stack right now
As of this writing, I use:

  • Hermes for everyday tasks. Emails, calendar, Google Doc edits, and honestly, therapy through voice replies. I switched over to Hermes because it’s more reliable than OpenClaw.
  • Codex and Claude Code for building things. When I’m coding, writing, or producing real work, I live in these apps. If I had to pick one, it’d be Codex due to the more generous rate limits

Edited:    |       |    Search Twitter for discussion