Startup Ideas Bank

A clever CRM thesis buried inside a very expensive problem with a very crowded graveyard.

AI roast score: 61/100 (C)

The idea

You did not invent CRM. You wrapped a durable agent around a system that already dies by trust, migration pain, and sales reps ignoring yet another tool.

In the founder's own words

trycompai/crm — An open-source, agentic-first CRM.

CRM


An open-source, agentic-first CRM.
A durable research agent is the product. The database is just where it writes things down.


The agent ·
Stack ·
Quick start ·
Configuration ·
Deploying ·
Contributing










What this is

Most CRMs are a database with a form in front of it. The AI ones bolt a chat box onto
the side of that form. Both leave the actual work — finding out what is true, and
writing it down — to a human who has better things to do.

This is built the other way round. The agent is not a feature of the CRM; the CRM is
where the agent keeps its notes. It runs on its own deployment, on its own schedule,
against its own work queue. It decides what to look at next, books its own follow-ups,
spends a research budget, and stops when the budget runs out. Nothing about it is
request-response: close the browser and it keeps going.

The API deliberately has no intelligence in it at all. NestJS reports that something
happened — a thread was ingested, a company was created, an attendee is unknown — by
writing a row to a queue. The agent leases that row and decides what it means. A Nest
service that calls an enrichment API is treated as a bug, and
docs/api.md explains the outage that made that a rule.

The rule the agent itself never breaks: nothing about a person is guessed. No tool
accepts a confidence score, because a model asked to grade its own certainty will, and
it will be wrong in the direction that makes it look useful. Tools report what they
observed — crm.signature-block , github.account-identity — and a ledger prices the
evidence. Strong evidence writes to the record. Weak evidence becomes a suggestion a
human settles. A confidently wrong fact about a customer is worse than a blank field,
because nobody can tell it is wrong.

It is single-tenant and internal by design. Sign-in is Google, the allow-list is one
environment variable, and everyone who gets in can see everything. That is the whole
authorisation model — see SECURITY.md before you point it at real
customer data.

Screenshots






Deals — filters, sort and page live in the URL, so a view is a link.





Contacts — most of these were created by the mailbox sync, not typed.







Companies — logo, industry and location arrive on their own.





Overview — yours or the whole team's, toggled in the URL.



The agent

apps/agent is its own deployment, built on
eve — Vercel's filesystem-first framework for durable agents.
A tool is a file, a skill is a markdown file, a schedule is a file, and the runtime
handles the durable part: sessions that survive a redeploy, work that resumes where it
stopped.







18 authored tools
read_crm_history , search_crm , identify_conta

The roast

This is smart engineering, but smart engineering is not a business. You are aiming at a market where buyers already hate switching, already have a CRM, and already get sold “AI” add-ons every week. The pitch says “an open-source, agentic-first CRM” and “the CRM is where the agent keeps its notes,” but that is still a CRM. That means long sales cycles, messy data migration, and brutal trust issues before anyone lets your agent touch real customer records. Your own story admits the hardest part: “nothing about a person is guessed,” “single-tenant,” “everyone who gets in can see everything,” and “see SECURITY.md before you point it at real customer data.” That is not a lightweight product. It is a controlled internal system for teams that can tolerate setup, governance, and risk. Yet your profile says you are a solo founder with no funding, standard pricing, product-led growth, and your biggest unknown is whether people will pay. That is a bad mix for a security-sensitive CRM. The idea also fights itself. You want open source and product-led adoption, but the core value is a durable research agent that spends budget, books follow-ups, and writes truth into a shared CRM. That is not a toy. It is a workflow system that needs trust, proof, and integration depth. Right now the pitch sounds like a technical philosophy, not a clear reason a buyer would rip out HubSpot, Pipedrive, or Salesforce and bet their revenue team on it.

Red flags

Verdict

This can work only if you prove one narrow team will pay for autonomous research inside CRM fast enough to overcome switching pain and trust fear.

Start with your own startup idea →

More ideas roasted by AI

Browse all startup ideas →