Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

qm – Multiplayer agent harness for work

github.com

Post reply on HN
Print view View original

171–180 of 186 posts

Re: qm – Multiplayer agent harness for work

#171

Post by maleldil »

fr2029 wrote: post #151
abustamam wrote: post #141

Earlier quoted context omitted.

My personal "tell" is that I use -- instead of em-dash. If you get a message from me with an actual "—" character it's almost certainly AI generated. I guess that's kind of my duress code :)

-- is n-dash and wrong. That's how you recognize an uneducated person. — is just opt-shift-hyphen on mac. no excuse for ascii n-dashes.

What if you're on Windows where it's much less convenient? Also, latex and others substitute that for the proper dash, so one might do it out of habit.

Also also,it's en-dash, not n-dash. And it's correct in British English, where the em-dash largely fell out of use.

Re: qm – Multiplayer agent harness for work

#172

Post by supermdguy »

nozzlegear wrote: post #78
supermdguy wrote: post #18

Earlier quoted context omitted.

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 quest…

> periodically checking slow DB queries and finding ways to speed them up. How does this work in practice?

It has read only access, so it’s able to check query statistics, find slow queries, then run EXPLAIN ANALYZE to find the root cause and either tweak the query or suggest indexes. A lot of it is low hanging fruit, I just haven’t put in the time to fix it (startup).

Re: qm – Multiplayer agent harness for work

#174

Post by jessejin »

argssh wrote: post #19

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

[dead]

Re: qm – Multiplayer agent harness for work

#176

Post by ignore_prev »

walrus01 wrote: post #68
recsv-heredoc wrote: post #64

Aren't there a ton of products already doing this? Why not just use claude Cowork? Surely they're simpler/better/more featureful/developed than the alternatives here? What advantage does this have? Would love to see a 'QM vs Cowork' comparison!

> Why not just use claude Cowork? Because people want to be able to do things like use their own clients of pi or opencode with LLMs they run themselves, such as the just released deepseek v4 flash 0731, not permanently tied to an Anthropic ecosystem of non-open-weight LLMs and pay forever per token.

[flagged]

Re: qm – Multiplayer agent harness for work

#177

Post by muretai »

bfeynman wrote: post #135

Can someone give me an example where this is truly and uniquely useful? I've seen so many of these things and I can't tell if part of it is like mostly for enabling nontechnical folks to do more things or if it's some unlock and additive value. At end of day beneath it all things are just prompts, and then you can provide tools and context, but even then that's not even something I've found that useful to keep becaus…

[flagged]

Re: qm – Multiplayer agent harness for work

#178

Post by recsv-heredoc »

samtheprogram wrote: post #112
recsv-heredoc wrote: post #66

Earlier quoted context omitted.

Kinda makes sense. Multiplayer is at odds with async, generally speaking - and LLMs/agents really see their productivity rise up with async work.

I disagree with this. If agents are doing asynchronous work, it's really an artifact anyone should be able to look at.

Realtime multiplayer - to clarify the position.

Re: qm – Multiplayer agent harness for work

#179

Post by epistasis »

2001zhaozhao wrote: post #59
epistasis wrote: post #37

It's fascinating to see new UI primitives and concepts get invented in the LLM era. The sea of creativity makes it hard to even understand most of what each new app does, and nobody describes them well. When I went to the Hermes agent web page, I was left with zero clue about what it did or what it could do. It took a bit of digging to find the right part of the qm page that helped me grok what was going on. I've bec…

It's really hard to focus on the unique aspect of your tool because it runs the risk that people will think it's unfamiliar and therefore not useful to them. That's why a lot of the tool marketing pages look the same even though the tools themselves might be different or innovative

Isn't it a bigger risk for people to see the page, understand nothing, and think it's not useful to them? Having no information, after investing time to investigate, leaves me with a very sour taste and makes me unlikely to give it a fair shake a second time.

Re: qm – Multiplayer agent harness for work

#180

Post by kuanzema »

How is QM trying to differentiate from HarnessRouter.ai, which launched on Launch YC about 10 days ago? https://www.ycombinator.com/launches/RpL-harnessrouter-bring...

Both seem to provide a unified interface across different harnesses/models. HarnessRouter exposes that as a developer API for embedding agent-powered features into products, with Task / Run / Session / Streaming / File / Artifact / Renderer contracts, plus tracing around harness/model behavior over time.

Is the main distinction that QM is a company workspace, while HarnessRouter is an embeddable harness layer for product teams and enterprises?

Post reply on HN