RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.
memcached development tree
DataLoader is a generic utility to be used as part of your application's data fetching layer to provide a consistent API over various backends and reduce requests to those backends via batching and caching.
groupcache is a caching and cache-filling library, intended as a replacement for memcached in many cases.
📦 Workbox: JavaScript libraries for Progressive Web Apps
LMCache: Supercharge Your LLM with the Fastest KV Cache Layer
A fast, light-weight proxy for memcached and redis
Garnet is a remote cache-store from Microsoft Research that offers strong performance (throughput and latency), scalability, storage, recovery, cluster sharding, key migration, and replication features. Garnet can work with existing Redis clients.
Open-source, low-latency key/value engine built on Valkey with query subscriptions and hierarchical storage tiers.
concurrent, cache-efficient, and Dockerfile-agnostic builder toolkit
Open-source, high-performance AI gateway that works as your LLM gateway, MCP gateway and agent gateway. One OpenAI-compatible API for 10,000+ models, with failover, load balancing, semantic caching, virtual keys, budgets and MCP Code Mode. Works with any SDK or agent and adds under 200µs of overhead at 5k RPS.
Easily find and remove old and heavy node_modules 📦, artifacts, caches and dev leftovers 🧹
- cli
- javascript
- build-artifacts
- cleaner
🚀 Next Gen Multi-tenant AI One-Stop Solution. Builtin Admin & Billing System. Enterprise-Grade Unified LLM Gateway Support for 200+ Models And 35+ Providers, Load Balacing w/ Priority-base Routing, Cost Management, Chat Share, Cloud Sync, Credit/Subscription Billing, All File Parsing, Web Search, Built-in Model Cache.
TranslatedCacheCloud is a Redis cloud management platform. It supports Standalone, Sentinel, and Cluster architectures for Redis, effectively reducing large-scale Redis operation and maintenance costs, and improving resource management and utilization. The platform provides rapid construction/migration, operation and maintenance management, elastic scaling, statistical monitoring, client integration and access and other functions
- redis
- redis-cluster
- java
- redis-cache
The highly customizable and versatile GraphQL client with which you add on features like normalized caching as you grow.
- graphql
- graphql-client
- exchange
- graphql-clients
TranslatedOpensabre is a microservice development platform based on SpringCloud2023, integrating components such as Spring Security and Springcloud Alibaba. It includes basic system management applications such as basic RBAC permission management, authorization and authentication, gateway management, service governance, and audit logs. It defines related development standards and styles and implements them in the service framework layer, works out of the box, and supports deployment with Docker and Kubenetes. It lets project developers get into business development quickly, without spending too much time on building the basic architecture and on coding style standards. The goal is to build a set of financial-grade, highly secure microservice solutions.
- springcloud
- springboot
- oauth2
- feign-client
TranslatedWeChat all-platform .NET SDK, Senparc.Weixin for C#, supporting .NET Framework, .NET Core, and .NET 10.0. Already supports all platforms including WeChat Official Accounts, Mini Programs, Mini Games, WeChat Pay, WeCom (Enterprise WeChat)/Enterprise Accounts, Open Platform, JSSDK, and WeChat peripherals. WeChat SDK for C#.
A fault tolerant, protocol-agnostic RPC system
An in-memory key:value store/cache (similar to Memcached) library for Go, suitable for single-machine applications.
Image loading system
bika 哔咔 全平台客户端。A comic browser,support Android / iOS / MacOS / Windows / Linux.
Performant React Native image component.
Semantic cache for LLMs. Fully integrated with LangChain and llama_index.
Efficient cache for gigabytes of data written in Go.