Partner program
You build the intelligence. SweetHive supplies the boundaries: scoping, audit, group targeting and on-prem runtime — the parts that get agent projects past IT and legal.
Every agent consultancy has lived this meeting: the demo lands, the client is excited — then someone asks “where does the data go?” and the project dies in security review. The blocker is rarely your agent. It's the deployment surface: flat permissions, no audit trail, no answer to “what can it see, for whom?”
Every agent you deploy inherits deployment scope ∩ each person's visibility — enforced in the platform's retrieval layer. You never build permission logic again, and your client's IT can verify it.
One agent, instanced per group or context, each instance with isolated memory and index. External partners, insurers, parents: separated by construction — for mixed-trust audiences.
Pin your agent to the client's private nodes — the agent goes to the data. “Nothing leaves your infrastructure” becomes a sentence you can say in the sales meeting.
Bring agents you've already built: SweetHive speaks MCP, so existing work connects through scoped tokens instead of a rewrite.
Every run logged with sources, effective scope and where it was computed. Your engagement report writes itself.
Develop your agent against the Agent API / MCP surface; package it as an app installable into contexts.
Install into the client's hive, scoped to their tree, with the audience and runtime they choose.
Run it under the client's audit and policies. Listed agents earn through the platform: revenue share on installed agents, plus your services.
Program terms, tiers and revenue share — to be defined.
Our first proof vertical is art & heritage, via the AerariumChain HUB — and the same two-tier pattern extends to every regulated, high-trust sector.
Build on the boundaries your clients' IT and legal teams already ask for.
Apply to partner