--- title: GitHub - yc-software/qm: Multiplayer agent harness for work description: QM is an open-source multiplayer AI agent harness designed for startups, giving each employee their own isolated workspace with scoped memory, files,... canonical: https://daily.dev/posts/github---yc-software-qm-multiplayer-agent-harness-for-work-y46pwxkg4 twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: GitHub - yc-software/qm: Multiplayer agent harness for work | daily.dev og:description: QM is an open-source multiplayer AI agent harness designed for startups, giving each employee their own isolated workspace with scoped memory, files,... og:url: https://daily.dev/posts/github---yc-software-qm-multiplayer-agent-harness-for-work-y46pwxkg4 og:image: https://api.daily.dev/og/posts/y46pWxKG4.png og:image:alt: GitHub - yc-software/qm: Multiplayer agent harness for work og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # GitHub - yc-software/qm: Multiplayer agent harness for work **[Hacker News](https://daily.dev/sources/hn)** · 7 min read · 2 upvotes · 0 comments ## Summary QM is an open-source multiplayer AI agent harness designed for startups, giving each employee their own isolated workspace with scoped memory, files, credentials, crons, and sandboxes. It integrates with Slack and a web UI, supports multiple AI coding harnesses (Claude Code, OpenCode, Codex, Pi), and allows collaborative agent use in channels and projects. The architecture uses a headless TypeScript/Node core with Fastify, Postgres for persistence, per-scope durable sandboxes, and a plugin system for Slack and web surfaces. Security postures range from strict (human approval per tool call) to auto (content screening) to dangerous. Organizations deploy it to their own cloud via a deployment repository pattern, with support for private forks and org-level customization. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Community take How the wider developer community reacted, aggregated from 1 discussion and 227 comments across hackernews (as of 2026-08-01). **TL;DR:** The community is skeptical but curious about QM, a YC-built multiplayer agent harness; most discussion centers on the irony of an AI project banning AI-generated contributions, the "anti-slop" design skill, and whether this is genuinely novel or just another over-engineered harness. **Sentiment:** 25% positive · 40% mixed · 35% skeptical **The case for** - The contribution model (human-written text/ideas only, no code PRs) is seen by some as a smart way to filter low-quality drive-by contributions and focus on idea quality. - Having an always-on agent with access to internal systems for tasks like CI fixes, RCA generation, and DB query optimization is seen as genuinely useful by practitioners. - Making it open source is appreciated, and some see it as a natural evolution of personal AI brain tools (like gbrain) extended to teams. **The pushback** - The "anti-slop" skill is criticized as self-defeating—banning em-dashes and specific color palettes will just create a new, equally recognizable AI aesthetic basin. - The 22,000-token skill is called out as bloated and poorly engineered, undermining trust in the overall harness. - Many commenters find the project over-engineered, gimmicky, and not clearly differentiated from existing tools like Claude Code/Cowork. - The README itself appears AI-generated, contradicting the project's stated anti-slop stance. - The novelty of the core concept (shared company AI brain/harness) is questioned, with commenters noting many similar products already exist. **By community** - hackernews (mixed): Commenters are split between genuine interest in the agent harness use cases and sharp criticism of the anti-slop skill's self-defeating logic, the project's bloat, and YC's apparent identity crisis in the AI era. **Hottest debate:** Whether banning AI stylistic tells (like em-dashes or specific color palettes) actually produces less "slop" or just shifts the slop to a new, equally recognizable pattern. **Open questions** - How does the shared 'company brain' actually develop and stay coherent when each employee runs their own harness instance? - What concretely differentiates QM from Claude Cowork or other multiplayer agent tools beyond the multiplayer framing? - Can you meaningfully prompt an AI agent to have genuine design taste, or does any rule-based approach just produce a new flavor of templated output? **Highlights** > Doesn’t this just lead to a new “basin of tastelessness” that, sure, looks different from current slop, but is itself just eventually slop all the same? > — [thoughtpeddler on hackernews · 2 comments](https://news.ycombinator.com/item?id=49128061) > All due respect to the YC folks, but having a skill with 22,069 tokens is a major skill issue. Yes, ironic. My slop control skill is a thousand tokens. Biggest problem I see with the skill is that everything is prompted via negativa. smh. sorry to be judgmental but it's hard to trust a harness that comes shipped with a skill like this. > — [postalcoder on hackernews · 2 comments](https://news.ycombinator.com/item?id=49131986) > i think it makes perfect sense and I'll probably adopt the same posture for my open source project. The idea is that the core dev team is the one with the AI harness. If someone contributes an idea they can just feed it to their AI to implement it and it probably costs 10 minutes of human time, because they trust that their harness will be able to implement the feature competently. So, because the implementation effort is so low, the only aspect that matters if the quality of the idea. It's way easier to screen human written text than a bunch of code in a PR. If you just give them code, they would not know if you made it with a competent harness. If you gave them a AI written design they would have a lot more to read through to decide whether it's slop. If you just give them an idea it's a lot easier to determine whether it's high quality. > — [2001zhaozhao on hackernews](https://news.ycombinator.com/item?id=49128568) > 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. > — [supermdguy on hackernews · 2 comments](https://news.ycombinator.com/item?id=49127232) > this looks over engineered, gimmicky and lame. YC is clearly having a "crisis of meaning" in a post AI world > — [gyanchawdhary on hackernews · 2 comments](https://news.ycombinator.com/item?id=49130390) **Source threads** - [hackernews](https://news.ycombinator.com/item?id=49126604) · 363 points · 227 comments ## Similar posts on daily.dev - [Introducing the QML Coding Skill for Agentic Workflows](https://daily.dev/posts/introducing-the-qml-coding-skill-for-agentic-workflows-zmhzr9ztm) · Qt · 0 upvotes · 0 comments --- Tags: [#typescript](https://daily.dev/tags/typescript), [#ai-agents](https://daily.dev/tags/ai-agents), [#postgresql](https://daily.dev/tags/postgresql), [#slack](https://daily.dev/tags/slack) [View this post on daily.dev](https://daily.dev/posts/github---yc-software-qm-multiplayer-agent-harness-for-work-y46pwxkg4) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"GitHub - yc-software/qm: Multiplayer agent harness for work","url":"https://daily.dev/posts/github---yc-software-qm-multiplayer-agent-harness-for-work-y46pwxkg4","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/github---yc-software-qm-multiplayer-agent-harness-for-work-y46pwxkg4"},"datePublished":"2026-07-31T18:55:37.863Z","dateModified":"2026-08-01T17:00:06.141Z","description":"QM is an open-source multiplayer AI agent harness designed for startups, giving each employee their own isolated workspace with scoped memory, files,...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/cdf84e87fb3f2c43459420f165eab29e?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/cdf84e87fb3f2c43459420f165eab29e?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Hacker News","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Hacker News","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/hn","url":"https://daily.dev/sources/hn"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/github---yc-software-qm-multiplayer-agent-harness-for-work-y46pwxkg4","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":2},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"typescript,ai-agents,postgresql,slack","timeRequired":"PT7M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Hacker News","item":"https://daily.dev/sources/hn"},{"@type":"ListItem","position":3,"name":"GitHub - yc-software/qm: Multiplayer agent harness for work"}]} ```