qm – Multiplayer agent harness for work • Hacker News Board

Re: qm – Multiplayer agent harness for work

#11

Post by embedding-shape » Fri, Jul 31, 2026, 6:48 PM UTC

Drupon wrote: post #2

>We take contributions as human-written text, not code — see CONTRIBUTING.md. Describe the change you'd like informally in a .txt or .md file in adrs/, and if we're aligned we'll handle the implementation. Report vulnerabilities privately — see SECURITY.md, not a public issue. Starting to think people were right when they talked about our industry itself having an AI psychosis problem.

Sounds to me they're asking people to basically at least put the starting stones to something that looks like a specification. Not a bad idea to gate the flurry of feature requests to people who actually can think 10-15 minutes about the feature they're suggesting/asking for.

Re: qm – Multiplayer agent harness for work

#12

Post by embedding-shape » Fri, Jul 31, 2026, 6:49 PM UTC

john_strinlai wrote: post #9

warkdarrior wrote: post #7

Earlier quoted context omitted.

They specifically ask not to create/submit a formal proposal. I do not see any restriction on the use of AI otherwise.

i read the emphasized " human-written " part, in combination with that last line, as a blanket restriction (for contributing). but perhaps i read it wrong.

List of commits already include at least two contributors who are openly working with Claude on their code: https://github.com/yc-software/qm/commits/main/

Re: qm – Multiplayer agent harness for work

#13

Post by dgellow » Fri, Jul 31, 2026, 6:50 PM UTC

Drupon wrote: post #2

>We take contributions as human-written text, not code — see CONTRIBUTING.md. Describe the change you'd like informally in a .txt or .md file in adrs/, and if we're aligned we'll handle the implementation. Report vulnerabilities privately — see SECURITY.md, not a public issue. Starting to think people were right when they talked about our industry itself having an AI psychosis problem.

I tend to think we have an industry AI mania problem, but I’m not sure I understand what you find psychotic about this. I find it better to get a text suggestion or description of the change, then work on the implementation myself, even without using an agent, instead of reviewing LLM diffs that I know I will want to tweak to my taste

Re: qm – Multiplayer agent harness for work

#14

Post by azuanrb » Fri, Jul 31, 2026, 6:51 PM UTC

yewenjie wrote: post #4

Is Hermes the best openclaw like agent as they mention running it before? Also, what are power uses really using openclaw like systems for?

I'm currently using it to help me with my oncall, first responder to our any production alerts. It's not as efficient as coding agent by default, but it's been tremendously helpful to me.

Re: qm – Multiplayer agent harness for work

#15

Post by jez » Fri, Jul 31, 2026, 6:51 PM UTC

Drupon wrote: post #2

>We take contributions as human-written text, not code — see CONTRIBUTING.md. Describe the change you'd like informally in a .txt or .md file in adrs/, and if we're aligned we'll handle the implementation. Report vulnerabilities privately — see SECURITY.md, not a public issue. Starting to think people were right when they talked about our industry itself having an AI psychosis problem.

SQLite has a conceptually similar contribution process:

> the project does not accept patches from random people on the internet

https://sqlite.org/copyright.html

In their case, it's motivated by a desire to keep copyrighted code out of the SQLite implementation, but I'm sure it has a nice benefit of making it so that an extremely widely used project doesn't get drive by, low effort code review requests while still allowing the community to engage.

Asking that "random people on the internet" don't sent code is not altogether a novel, post-AI idea.

Re: qm – Multiplayer agent harness for work

#16

Post by j45 » Fri, Jul 31, 2026, 6:53 PM UTC

ronsor wrote: post #8

john_strinlai wrote: post #3

i find something a bit funny in an ai project, written by ai, requiring human-written text with specific guidance to not use ai. " Given that coding agents write most underlying code now, we'd prefer PRs in the form of human-written text. [...] Please do not have AI artificially expand what you'd like to do into a formal proposal. "

Coding agents are extremely useful but often extremely dumb with design. If you do not design the software yourself, you will probably get slop. This was always the core issue with vibe coding.

AI Averages, and is inclined to do average designs and implementations, which in some cases might be an improvement, but long term it creates more to deal with.

Re: qm – Multiplayer agent harness for work

#17

Post by backscratches » Fri, Jul 31, 2026, 6:53 PM UTC

yewenjie wrote: post #4

Is Hermes the best openclaw like agent as they mention running it before? Also, what are power uses really using openclaw like systems for?

Hermes is huge and packed with features you probably don't need. I prefer smaller one I can extend as necessary, there are so many on github now and it is fun to test them but have been impressed with dirge (https://github.com/dirge-code/dirge) not affiliated.

I have one reading my second tier RSS feeds and newsletters and giving me news/market updates filtered for things important to me

Re: qm – Multiplayer agent harness for work

#18

Post by supermdguy » Fri, Jul 31, 2026, 6:57 PM UTC

yewenjie wrote: post #4

Is Hermes the best openclaw like agent as they mention running it before? Also, what are power uses really using openclaw like systems for?

Still figuring it out, but it's been really convenient to have an always-on agent that has access to internal systems and can be triggered by webhooks. Some examples of what we use it for:

- automatically fixing simple CI failures

- getting production alerts and automatically creating RCAs and a fix PR

- periodically checking slow DB queries and finding ways to speed them up.

- creating charts to answer one-off questions about our data

I've tried using it as an on-the-go coding agent as well, but found I prefer more interactive agents, so I can see what the code looks like.

Re: qm – Multiplayer agent harness for work

#19

Post by argssh » Fri, Jul 31, 2026, 6:58 PM UTC

it says "Each deployment runs in the operator's own cloud account"

But feels like its written to run on one mac/vm and carries same drawbacks of other similar platforms. I'd rather use Hermes/Openclaw for oss or closed managed agents like Tasklet or Prajvis

Re: qm – Multiplayer agent harness for work

#20

Post by nisegami » Fri, Jul 31, 2026, 7:00 PM UTC

backscratches wrote: post #17

yewenjie wrote: post #4

Is Hermes the best openclaw like agent as they mention running it before? Also, what are power uses really using openclaw like systems for?

Hermes is huge and packed with features you probably don't need. I prefer smaller one I can extend as necessary, there are so many on github now and it is fun to test them but have been impressed with dirge ( https://github.com/dirge-code/dirge ) not affiliated. I have one reading my second tier RSS feeds and newsletters and giving me news/market updates filtered for things important to me

I had the same line of thought and spent a while with nanoclaw before realizing that adding the features I want back in would have made future updates too painful. I ended up switching to Hermes and aggressively disabling tools/skills and it's been pretty fine so far. I got more use cases set up than I did in my time with nanoclaw.