Home
KwaaiNet is a decentralized AI node architecture for Layer 8 — the trust and intelligence layer above the traditional network stack — built by the Kwaai Foundation, a 501(c)(3) nonprofit AI lab focused on democratizing AI.
Each KwaaiNet node combines a decentralized trust graph (cryptographic identity, verifiable credentials, local trust scores), shared sharded LLM compute over heterogeneous CPUs/GPUs using Petals-style distributed inference, secure multi-tenant knowledge storage via Virtual Private Knowledge (VPK) with encrypted vector search, and intent-based peer-to-peer networking that routes based on "what I need" — model, trust tier, latency — not just IP addresses. From an app's point of view, KwaaiNet looks like a familiar chat-completion style HTTP API; under the hood it is a person-anchored Layer 8 fabric where every node is tied to an accountable human or organization.
- Decentralized trust graph — Ed25519-anchored identity, W3C Verifiable Credentials, and a local time-decayed trust score; no central trust registry.
- Sharded LLM compute — Petals-style block-sharded inference with RoPE, GQA, SwiGLU, per-session KV cache, and an OpenAI-compatible HTTP API.
- Virtual Private Knowledge (VPK) — Multi-tenant encrypted vector search bound to node identity and credentials, with DHT advertisement.
- Intent-based networking — Nodes route requests based on intents like "model X, minimum trust tier Verified, max latency Y," making the network semantic and economic, not just transport.
| Page | Description |
|---|---|
| Getting Started | Install the kwaainet CLI, initialize a node, and make your first API call |
| API Quickstart | Call the OpenAI-compatible API from curl, Python, and JavaScript |
| Architecture | Node architecture, lobes, trust graph layers, and the Layer 8 stack |
| Sharded LLM Processing | How CandelEngine shards transformer models across nodes and manages KV cache |
| Network and Intent Routing | P2P fabric, trust-gated routing, and the full intent lifecycle |
| Reputation and Trust | Local trust scores, EigenTrust propagation, and endorsement accountability |
| Roadmap | Layer 8 destination vs current implementation vs gaps and contribution ideas |
| Contributing | How to contribute — 1 hour / 1 day / 1 week entry paths |
KwaaiNet is developed by the Kwaai Foundation, a 501(c)(3) nonprofit AI lab and proud signatory of the GliaNet Fiduciary Pledge. Kwaai collaborates with the Linux Foundation Trust Over IP (ToIP) Decentralized Trust Graph Working Group, Mozilla / Mozilla.ai, SingularityNET, and IEEE P7012.
Learn more at kwaai.ai and the Kwaai-AI-Lab GitHub organization.
Part of the KwaaiNet project · View source docs