I think it was obvious, yet nobody seemed to have released a version people could actually easily use.

The feature set is pretty simple:

- Agents that can write their own tools.

- Agents that can write their own skills.

- Agents that can chat via standard chat apps.

- Agents that can install and use cli software.

- Agents that can have a bit of state on disk.

> nobody seemed to have released a version people could actually easily use

Yet I’ve known many people who have said it is difficult to use; this was a 0.01-0.1% adoption tool. There is still a huge ease of use gap to cross to make it adopted in 10-50% of computer users.

Yeah - people are hungry for it. They tolerate the kind of crappy docs and difficulties.

thats by design, you know all those huge security implications. now image if it was so easy to setup and install and use.

good summary. i think you forgot heartbeat.md which powers some autonomy.

do you think the agent admin ui mattered at all?

other contributors while i think of them:

- good timing around opus 4.6 as the default model? (i know he used codex, but willing ot bet majority of openclaws are opuses)

- make immediate wins for nontechnical users. everyone else was busy chasing cursor/cognition or building horiztonal stuff like turbopuffer or whatever. this one was straight up "hook up a good bot to telegram"

- theres many attempts at "personal OS", "assistant", but no good ones open source? a lot of sketchier china ones, this was the first western one

Aren't all of these things you can do with Claude Code? Granted, the chat app one is novel, but you could ask Claude Code to set that up.

Thats basically what this guy did. He vibe coded a chat interface.

Most things that go viral actually have a concerted marketing push behind them. I suspect that was the case here. Something about the way people talked about it didn't come across as very genuine.

As someone who attended numerous meetups from the author and saw the vibe among those events, believe me it was as genuine as it can get.

do you genuinely think that numerous meetups isn't a marketing push?

Well, you can argue that tech meetups in general are a form of marketing - but this wasn't really a 'company X hosts a react meetup trying to find people to work there' type of thing. Many drove for hours just to attend.

Getting dozens of people in the same room, excited about technology is not trivial, and having hundreds of people show up is relatively hard in a city like Vienna which doesn't have a vibrant tech scene. Sure, some people come to find job opportunities or for free food, but many 'established' meetups sometimes just have a few attendees, so this on its own is not a small task. Peter definitely didn't have time to focus on this given everything else that was going on. So for Vienna, this is pretty much as viral as it gets.

Not sure about other cities where this took place.

by your definition, what is marketing then?

It's another game where software quality, security of novelty is not an outcome-defining factor.