Aid-On

高精度なLLMレート制限ライブラリ - Precise dual rate limiting for LLM APIs (RPM + TPM)

高度なスコアリングアルゴリズムを備えたLLMリクエスト用キューディスパッチャー - LLM Queue Dispatcher for LLM requests with advanced scoring algorithms

Edge-native unified LLM provider - pure fetch API, minimal dependencies (zod), WebStreams, memory optimization for Cloudflare Workers and edge computing environments

FractoP - Fractal Processor for infinite-length text processing with LLMs

Templex - Template Extractor for extracting abstract templates and document structures from articles and text

Time-aware memory system that understands when things happened, not just what happened

Vercel AI SDK対応のインメモリRAG実装 - In-memory RAG implementation with Vercel AI SDK support

Neural Signal Processing for LLM Agents - Stimulus → Synapse → Response → Signal

Vercel AI SDK wrapper for @aid-on/unillm - provides LanguageModelV1 compatibility for existing AI SDK code

EmbersM - Cloudflare Native Memory System with 5-Layer Architecture

Unified STT (Speech-to-Text) provider for Cloudflare Workers AI / Groq

Silero VAD wrapper for browser - voice activity detection

Aid-On Design System - Design tokens and utilities for Qwik applications

Edge-native authentication with Fluent API. Sessions, OAuth, Guests, Audit logs. Zero Node.js dependencies.