Manuk Minasyan

Manuk Minasyan

RelaticleRelaticle
Founder, Relaticle (open-source CRM)

About

Building Relaticle, an open-source CRM where AI agents work on real customer data and every in-app write is a proposal a person approves. Two years in, mostly solo, on Laravel and Filament. I also maintain the Custom Fields package the CRM is built on. Self-hosting, MCP, and honest tradeoffs over long feature lists. Ask me anything about running agents against a CRM.

Badges

Tastemaker
Tastemaker
Gone streaking 10
Gone streaking 10
Gone streaking
Gone streaking
Gone streaking 5
Gone streaking 5

Maker History

  • Relaticle
    RelaticleOpen-source CRM with approval-gated AI writes
    Sep 2026
  • Marmof
    MarmofOriginal material for your site, emails, ads, and blogs
    Aug 2023
  • 🎉
    Joined Product HuntMay 20th, 2023

Forums

Where should the approval line sit for AI writes in a CRM?

I am launching Relaticle here next Tuesday. It is an open-source CRM where AI agents can do real work on your data, and I want feedback on one design decision before launch day.

Relaticle has two trust levels. External agents (Claude Desktop, Cursor, any MCP client) authenticate over OAuth and write through 37 tools directly, like an API client. The in-app assistant is stricter: every write it wants to make becomes a proposal card, and a person approves or skips it record by record before anything lands.

The question I keep going back and forth on: is per-record approval the right granularity, or does it become noise once you trust the assistant? Would you want a "trust this kind of change" switch, or does that defeat the point?

If you run a CRM with any AI in it today, I would like to hear where you draw that line. The whole thing is AGPL and self-hostable, including the model via Ollama, so you can look at how it works rather than take my word for it.

•

23d ago

Relaticle - Open-source CRM with approval-gated AI writes

Most CRMs bolt AI on. Relaticle is built agent-first: any MCP client gets 37 first-party tools over OAuth, with workspace custom fields in each agent's schema automatically. The in-app assistant is stricter: every write is a proposal showing the exact change, approved record by record. Self-host everything under AGPL, including local inference with Ollama. Free forever self-hosted; Cloud is flat per-workspace pricing, not per-seat.
View more