Agents
An agent per partner, with its own tools and memory. Their customers never see another partner’s context.
The models you already meant to use
Gemini, Gemma, or a compatible endpoint. No rewrite of the partner’s stack.
Shaped to the traffic
Chat, batch, or a spike at month-end. The endpoint follows the load.
You keep the face of it
We run the runtime. The partner sees your product, not ours.
from orbysoft import Agent, tool
agent = Agent(
model="gemini-2.5-flash",
region="southamerica-east1",
memory="per_partner",
monthly_cap=1200,
)
@tool
def crm_lookup(lead_id: str) -> dict:
return crm.get(lead_id)
@agent.partner_scoped
def qualify(lead):
return agent.reason(lead, tools=[crm_lookup])$ orby run qualify --partner atlas-spscopeatlas-sp · isolatedmodelgemini-2.5-flash · 42msresultscore=86 next=book_demo
