KwaaiNet

Infraestructura P2P

A volunteer-operated P2P distributed AI inference network that shards large language model weights across participating nodes, enabling community-run AI computation without centralized cloud infrastructure. Built on the Petals framework (legacy Python implementation, OpenAI-Petal); being rewritten in Rust with WASM + WebGPU for browser and mobile deployment. Operated by Kwaai, a 501(c)3 nonprofit focused on democratizing personal AI through self-sovereign, privacy-preserving principles.

Comunidad

Detalles

Licencia CC-BY-4.0 (OpenAI-Petal); CC0-1.0 (repo license) https://github.com/Kwaai-AI-Lab/KwaaiNet
Estado de Desarrollo 🔬 Beta
Detalle del Estado de Desarrollo Beta (legacy Python/Petals node operational; Rust rewrite in active development targeting Q1 2026 browser launch)
Propietario Kwaai AI Lab (501c3 nonprofit)
Órgano de Gobierno Kwaai AI Lab (501(c)(3) non-profit)
País USA
Año de Inicio 2023
Stack Python + Shell (legacy OpenAI-Petal); Rust + WASM + WebGPU (KwaaiNet rewrite in progress)
Financiamiento Nonprofit (501c3); donations via Zeffy; undisclosed grants
Última Investigación 1 jul 2026

Dominios de Caso de Uso

Evolución de Plataformas y Soberanía

Infraestructura P2P Atributos

Orígenes Distributed AI inference / Personal AI
Base de Datos N/A (inference routing infrastructure, no application data store)
Formatos de Datos OpenAI API-compatible JSON (chat/completions endpoints); arbitrary LLM token streams
Soporte Móvil N/A (legacy); Planned — iOS/Android Q2–Q3 2026 (Rust rewrite)
Soporte Web N/A (legacy); Planned — browser extension Q1 2026 (Rust rewrite)
Aplicaciones Nativas Yes — Linux and macOS installers; Docker/Podman containers; CLI daemon management
Términos Free (volunteer node operation; no compensation to node operators)
Fondos Undisclosed
Basado En Petals (distributed inference framework, legacy); BigScience / Together AI Petals protocol
Arquitectura P2P DHT-based P2P mesh; nodes contribute model shards; bootstrap peers for initial discovery; OpenAI-compatible API gateway layer
Red de Superposición Global (nodes distributed across public network; map.kwaai.ai provides node visibility)
Direccionamiento por Contenido No
Local-First N/A (inference routing, not storage)
Cifrado de Extremo a Extremo (E2EE) No (data passes through participating nodes; node operators can observe inference traffic)
Tolerancia a Fallos Bizantinos No
Firma N/A
Permisos N/A (open relay; no cryptographic access control on inference requests in current implementation)
Madurez del Protocolo / Estandarización Community Standard / Pre-specification (Petals protocol underlies legacy implementation; KwaaiNet Rust rewrite is pre-specification)
Función de Infraestructura Distributed compute (AI inference)
Modelo de Amenazas N/A (not designed as censorship circumvention infrastructure; primary threat is model weight confidentiality and inference privacy)
Modelo de Nodo Voluntario Volunteer-operated (community nodes); Foundation-operated (Kwaai operates bootstrap/coordination infrastructure)
Visibilidad del Tráfico Content visible to intermediate nodes (model shard holders observe token fragments during inference; E2EE not implemented)
Escala de Despliegue Activo ~100 active nodes (legacy OpenAI-Petal network, developer/enthusiast community); KwaaiNet Rust rewrite pre-deployment