Kvasir network

A decentralized AI-inference network (DePIN) where everyday devices serve open models and earn KVR.

Kvasir is a decentralized AI-inference network: large open models are split across shared hardware with the p4 engine, so no single node has to hold the whole model. Anyone can contribute a GPU, CPU, NPU — even a phone — and earn KVR for the layers or experts their device actually serves. Developers reach the network through OpenAI/Anthropic-compatible gateways and pay per inference.

• Source-available engine — p4 is licensed under the Business Source License 1.1 (non-monetized internal use is permitted; hosted or revenue-generating use requires a commercial license); the llama.cpp data plane underneath stays close to upstream and inspectable.
• Self-custody wallet — keys never leave the user's device, and rewards are paid to each node owner's own Solana wallet. On devnet, staked KVR and prepaid credits are held by the gateway's treasury and tracked in its ledger until an on-chain staking program ships.
• Proven on real hardware — a 122B model has run end to end across 3 physical machines on our test fleet, with per-node contribution credited end-to-end.
• Named after the Norse myth — Kvasir, the wisest being, born from the pooled essence of every god and owned by none.

client SDK ──▶ gateway (OpenAI/Anthropic API, KVR settlement)
        ──▶ bridge (session · submit · gather)
        ──▶ serving topology: pipeline ring over layer windows,
            or expert-swarm dispatch at (layer, expert-range) grain
        ──▶ token streams back · each node's contribution is credited

Roles stack: one machine can be a compute node, a gateway host and a bridge host at once, and its rewards sum. The network's job is to make the aggregate look like one machine — one endpoint in front, thousands of imperfect devices behind.

Today the network runs on Solana devnet; KVR is a utility / contribution token, not a tradable asset or investment, and nothing on this page is financial advice.