OSAII · Cozy SwarmDeveloper docs ↗
VOLUNTARY DISTRIBUTED INFERENCE · V1.0

Install. Opt in.
Make room.

Cozy Swarm turns spare consumer CPU and GPU capacity into locality-aware model microclusters. Workers connect outward, receive verified model shards, and keep the request path OpenAI-compatible.

A network with boundaries

The coordinator schedules consecutive transformer layers onto workers that can communicate efficiently. KV caches stay with their stage owner. Volunteer machines never execute user code, and Community workloads are labeled before data leaves the API boundary.

Coarse partitions

GPT-2, Llama, and Qwen2 dense adapters use complete blocks per shard. WAN synchronization does not happen per matrix multiplication.

Explicit consent

Contribution starts disabled. CPU, GPU, RAM, VRAM, disk, bandwidth, schedule, battery, and metered-network limits are local settings.

Recoverable sessions

Heartbeats, observed reliability, circuit quarantine, pinned topologies, and bounded prefix replay handle volunteer disconnects.

Platform API key → OSAII edge safety gate → native coordinator → locality-aware topology → stage 0 → encoded activation → stage 1 → logits

Built for this Platform

OSAII owns the public /cozy/api route, scoped API keys, worker enrollment, and the safety boundary. The native coordinator is private and runs controlled model execution; the Worker never runs weights or volunteer code.

cozy worker init --coordinator https://osaii.wyvernhub.net/cozy/api
COZY_ENROLLMENT_KEY=cozy_enroll_... cozy worker enroll
cozy worker start

Privacy classes

TRUSTED is the default request class and requires administrator-assigned machines. New workers start in COMMUNITY; that class is opt-in per request with an explicit consent header. The scheduler never silently routes Trusted work to Community workers.