Self-Optimizing Neural Architecture (SONA) - Runtime-adaptive learning with LoRA, EWC++, and ReasoningBank for LLM routers and AI systems. Sub-millisecond learning overhead, WASM and Node.js support.
Ultra-fast MicroLoRA adaptation for WASM - rank-2 LoRA with <100us latency for per-operator learning
Semantic router for AI agents - vector-based intent matching with HNSW indexing and SIMD acceleration
Standalone vector database with SQL, SPARQL, and Cypher - powered by RuVector WASM
RuVector Format Node.js native bindings
RuVector Format Node.js native bindings
Modern and scalable routing for React applications
Advanced AI vector database CLI for PostgreSQL - pgvector drop-in replacement with 53+ SQL functions, 39 attention mechanisms, GNN layers, hyperbolic embeddings, and self-learning capabilities
High-performance synthetic data generator for AI/ML training, RAG systems, and agentic workflows with DSPy.ts, Gemini, OpenRouter, and vector databases
FaaS (Function as a service) framework for writing portable Node.js functions
base library for oclif CLIs
Next generation testing framework powered by Vite
[](https://serverless.com)
Modern and scalable routing for React applications
Modern and scalable routing for React applications
Modern and scalable routing for React applications
LangGraph
Modern and scalable routing for React applications
Modern and scalable routing for React applications
Modern and scalable routing for Web applications
Generic extension manager for WebSocket connections
The Serverless Dashboard plugin
Nest - modern, fast, powerful node.js web framework (@common)
Official SDK for Inngest.com. Inngest is the reliability layer for modern applications. Inngest combines durable execution, events, and queues into a zero-infra platform with built-in observability.