How Humonix is built.
One OS, a Brain per business.
For engineers and investors: the layers behind Humonix, the stack each one runs on, and the rules that keep AI agents safe inside a business.
How a request moves
The layers
| Agent | Read records | Draft | Change a price | Send an email | Move money |
|---|---|---|---|---|---|
| Quotes | Yes | Yes | Approval | Approval | No |
| Replies | Yes | Yes | No | Approval | No |
| Reorders | Yes | Yes | No | Approval | Approval |
| Collections | Yes | Yes | No | Approval | No |
Example policy Quotes → Change a price: the agent drafts, a person decides.
How we build
The stack
| Layer | Stack | Hosting |
|---|---|---|
| humonix.com site | Vite, React, prerendered pages, English and French | Fly.io, Toronto |
| HQ | Next.js 16, Node, SQLite + Litestream | Fly.io, Toronto |
| Allometry | Next.js 16, TypeScript, Postgres + Drizzle, Inngest, Clerk, WorkOS, Sentry | Not yet in production |
| Models | Anthropic Claude (default), OpenAI, Google, open-weight models, TypeSafe Jev for fast typed decisions | Providers, or local for region-pinned tenants |
| Interfaces | MCP (JSON-RPC 2.0), REST API, webhooks |
Questions
Is the Brain a data lake?
Not in the usual sense. A data lake stores raw data for analysts. The Brain keeps the data agents need (customers, products, prices, documents) with the business’s know-how and every approved decision, in one shared data model, and connects to the systems where the rest lives. The business owns it and can export it any time.
What do you mean by harness?
The layer around AI agents that makes them safe in a business: it gives them data and knowledge, limits what each can access, decides what needs an approval, and logs every action.
Can a client bring their own model keys?
Yes. They then pay the provider directly, and the gateway uses their keys. See the platform fee page.
Where is data hosted?
In North America, close to you: Toronto by default, with your own US instance on request. It is never used to train shared models.
Do you use MCP?
Yes, both ways: Allometry exposes its tools over MCP, and Hue answers inside Claude and ChatGPT through a public, read-only connector, in early access.
Build it with us
An early-stage, founder-led company building an operating system for SMBs, in English and French. If this is the work you want to do, say hello, even if the role isn’t listed yet.
Talk to us