Startup Ideas Bank

A smart internal agent layer, but right now it is mostly a technical thesis looking for a painful buyer.

AI roast score: 68/100 (C)

The idea

This is not a product yet. It is a very clever way to let startups give each employee their own agent sandbox and then pray someone pays for the privilege.

In the founder's own words

yc-software/qm — Multiplayer agent harness for work

qm

A multiplayer agent harness for work. In Slack and on the web.

What is QM?

Most agents are designed like personal assistants. You can make one work for a whole
company, but it quickly gets complex. QM is designed for startups. Employees each get
their own isolated workspace and work independently without affecting each other, and
they can also collaborate with the agent in channels, group messages, and projects.

Each person and each room has its own scoped memory, files, keychain view, permissions,
crons, web apps, and durable sandbox.

It's built with open source in mind. Pick your own harness and model and switch between
them — Pi, OpenCode, Codex, and Claude Code all drive the same core, so a deployment
isn't tied to any single vendor.

Features


Personal and shared scopes. People customize the agent to be theirs , and still
work with it collaboratively in Slack channels and projects.

Slack and web. The same identity and configuration carries between Slack and the
web app.

Admin control. Set org-level configuration, a security posture, and which
harnesses and models are available.

Web apps. Spin up custom internal apps and publish them to the right people.

Shared skills. Skills are scope-owned and shareable by grant, with admin-gated
promotion to the whole org and skill packs imported from git repositories.

Background work. Crons and watches run work while nobody's watching.

What you can do with it


Search internal notes, email, documents, databases, and the web together

Retrieve information from your company brain

Build internal apps, publish them to the right people, and keep their data current

Learn your writing voice from past sends, then triage your inbox on a schedule —
labels and reply drafts included

Work in an existing repository: run tests, open PRs, monitor CI, check system logs

Track a project in a shared channel and post updates and follow-ups

Architecture



flowchart LR
DB[("Postgres<br/>sessions · memory · queue")]

subgraph CORE["Headless core"]
API["API · identity · policy · scheduler"]
LOOP["Agent loop<br/>(Pi, OpenCode, Claude Code)"]
API <--> LOOP
end

SBX["Per-scope sandbox<br/>files · tools · logged-in services"]

DB <--> API
LOOP <--> SBX






Loading



Every turn runs through a central core, which can use a variety of models and harnesses
to generate the response. A Postgres persistence layer holds user data, session history,
and other durable state. The agent has a small, fixed tool surface; one of those tools is
execute , which runs commands in the scope's own isolated sandbox — its durable computer,
where installed tools stay installed. The web UI, the admin panel, and the public portal
are optional plugi

The roast

You built for the part of the market that likes demos, not the part that signs checks. The pitch says “for startups,” “in Slack and on the web,” and “subscription, license” with deal sizes of “1k_10k,” which means you are aiming at buyers who expect clear ROI fast. But the core story is still a stack of features: scoped memory, keychains, sandboxes, crons, shared skills, and model switching. That is architecture, not a reason to buy. The best version of this product is real, but the hard part is ugly. If each person gets an isolated workspace, permissions, and durable sandbox, you are selling trust, not just automation. That means security review, admin setup, permission errors, and support burden. Startups do want this, but they also churn fast and hate tools that need a long setup before value shows up. The biggest problem is that your pitch is trying to be both a general agent platform and a work product. “Search internal notes, email, documents, databases, and the web together” is broad, but broad is where incumbents and in-house scripts already live. Without a narrow first use case, you will lose to simpler tools that do one job well, or to teams that just duct-tape models onto Slack themselves.

Red flags

Verdict

Pick one painful work task, prove someone will pay for it, and stop selling the whole agent universe before you have a buyer.

Start with your own startup idea →

More ideas roasted by AI

Browse all startup ideas →