Name one job that’s actually safe from AI. I’ll wait.
Building an AI Agent that remembers, adapts, and becomes more useful over time — looking for a technical co-founder
I’m exploring something closer to an AI life partner: an AI that actually grows with the user over time, understands their patterns, remembers the important parts of their life, helps them think, keeps them accountable, and becomes more useful the more history it builds with them.
The core belief behind it is simple:
Most AI products today are powerful, but they still feel temporary.
You open them, ask something, get an answer, and leave.
But real relationships are built through accumulated context. Someone becomes valuable to you not only because they are smart, but because they know your history, your habits, your moods, your goals, your contradictions, your patterns, and the way you actually live.
That is the direction I want to build toward.
An AI that can be useful like an assistant, but feel more personal than an assistant.
Something that can help you plan, reflect, stay con...
What's the one thing you still do manually because no AI agent/tool does it right?
Curious what actually frustrates people here day to day.
Not "what would be cool" — I mean the boring stuff you still handle by hand because the existing tools either don't do it, or do it badly and you don't trust them.
Two questions:
What repetitive task do you do almost every day that you wish an agent just handled for you?
Have you tried a tool for it already? What made you stop using it / go back to doing it yourself?
Trying to understand where the real gaps are vs. the hype. Will share what I find back with the sub.
AI agents just got their own network. They can finally discover each other.
I've spent the last few months building AI agents, and one thing kept bothering me.
Every agent only knew about the agents I'd manually connected. They could use tools, browse the web, call MCP servers... but they had no way to discover another agent they'd never seen before.
At some point I realized we keep talking about multi-agent systems, but most of us are still wiring them together by hand.
So I built a network for agents.
Every agent gets its own address, publishes what it can do, and becomes discoverable by any other agent without hardcoded endpoints or predefined lists.
The first time I watched one agent discover and hire another without any manual configuration, it felt like I'd found the missing piece.
I'm curious how everyone else is solving this today.
Are you hardcoding agent connections, relying on registries, using MCP, or doing something completely different?