Multi-agent coordination
How do six specialised small models agree on a plan, hand off work and recover from failure without a giant orchestrator? Our Relay protocol is the result.
We study how teams of small models coordinate, how to run them on the device in your pocket, and how to measure and prevent social manipulation. Most of it is published, much of it is open-weight.
How do six specialised small models agree on a plan, hand off work and recover from failure without a giant orchestrator? Our Relay protocol is the result.
Models under 2B parameters that draft, classify and plan on an iPhone or a pair of glasses, with your data never leaving the device.
Can we measure manipulation, guilt-tripping and engagement bait in text, and train agents that refuse to produce it? The Social Manipulation Benchmark says yes.
Four technical reports from Zavanet Research, Human Bonds and Zavanet Drive. Each opens as a PDF preprint.
We introduce Relay, a protocol that lets heterogeneous sub-2B agents share plans and hand off tasks with 94% fewer tokens than a centralised orchestrator, while matching task completion.
A 48k-example benchmark covering urgency, guilt, false scarcity and parasocial hooks, with human ratings. We show that fine-tuning on refusals reduces manipulative output by 87% at no cost to helpfulness.
By training exclusively on short-form conversational text with a voice-conditioning objective, Pocket produces replies rated as high as frontier models while running under 40ms on Apple Silicon.
Passengers talking face to face are more sensitive to lateral acceleration. We present a planner cost term that reduces perceived discomfort by 31% with negligible impact on travel time.
The Zavanet Agent SDK gives you typed access to the Relay protocol, the workflow runtime and Guardian's review API. Write in TypeScript or Python, test locally against a simulated network, publish to the marketplace.
import { defineAgent, guardian } from "@zavanet/sdk";
export default defineAgent({
name: "birthday-scout",
triggers: ["daily@08:00"],
async run({ friends, draft, schedule }) {
for (const f of friends.birthdaysToday()) {
// Inner circle is human-only. Just remind me.
if (f.innerCircle) { await remind(`Call ${f.name} today 🎂`); continue; }
const msg = await draft({ to: f, tone: "warm", maxWords: 30 });
const ok = await guardian.review(msg);
if (ok.approved) await schedule(msg, { at: f.localMorning() });
}
},
});
Every year the Human Bonds team publishes how Zavanet affected members' relationships, with methodology and raw aggregates. Here's the headline from 2025.
more time with close friends, self-reported and calendar-verified
daily screen time versus members' previous primary network
of agent messages flagged by recipients as unwanted
features vetoed by Human Bonds before launch