| Name | Version | Summary | date | 
        
        
            
                | yokedcache | 
                0.3.0 | 
                Python caching library for FastAPI with Redis auto-invalidation, vector search caching, and intelligent cache management | 
                2025-11-03 05:05:39 | 
            
        
            
                | GeneralManager | 
                0.22.0 | 
                Modular Django-based data management framework with ORM, GraphQL, fine-grained permissions, rule validation, calculations and caching. | 
                2025-11-02 15:29:28 | 
            
        
            
                | ravyn | 
                0.3.0 | 
                Ravyn combines performance, type safety, and elegance. A next-generation async Python framework for APIs, microservices, and web applications. | 
                2025-11-01 19:23:13 | 
            
        
            
                | lilya | 
                0.22.9 | 
                Yet another ASGI toolkit that delivers | 
                2025-11-01 11:25:03 | 
            
        
            
                | fastpgcache | 
                0.1.8 | 
                A fast Redis-like caching library using PostgreSQL with UNLOGGED tables for high performance | 
                2025-10-26 02:31:12 | 
            
        
            
                | fastapi-orm | 
                0.11.0 | 
                A production-ready ORM for FastAPI with async support, automatic Pydantic integration, and Django-like syntax | 
                2025-10-24 00:26:06 | 
            
        
            
                | woosailibrary | 
                1.1.0 | 
                AI Output Token Optimizer - Reduce OpenAI API costs by up to 88% | 
                2025-10-23 09:40:05 | 
            
        
            
                | krl-core | 
                0.1.1 | 
                Shared foundation utilities for the KR-Labs analytics platform | 
                2025-10-20 02:16:44 | 
            
        
            
                | llm-dispatcher | 
                1.0.0 | 
                Intelligent LLM dispatching with performance-based routing, multimodal support, streaming, monitoring, and comprehensive analytics | 
                2025-10-18 09:57:57 | 
            
        
            
                | claude-cache-savings | 
                0.1.0 | 
                Calculates Anthropic Claude cost savings from use of prompt caching | 
                2025-10-17 20:22:38 | 
            
        
            
                | codesonor | 
                0.4.1 | 
                AI-Powered GitHub Repository Analyzer - 8 LLM providers (Gemini, OpenAI, Claude, Mistral, Groq, OpenRouter, xAI, Ollama), caching, quality scoring, exports, watch mode, dashboard | 
                2025-10-10 23:20:32 | 
            
        
            
                | omnifetch | 
                1.0.0 | 
                Multi-source data retrieval with intelligent caching and storage backends | 
                2025-10-10 20:41:15 | 
            
        
            
                | universal-scraper | 
                1.8.0 | 
                AI-powered web scraping with customizable field extraction using multiple AI providers | 
                2025-09-11 11:41:06 | 
            
        
            
                | hyperllm | 
                1.0.1 | 
                A unified interface for multiple LLM providers with caching and interactive development mode to get massive cost savings. | 
                2025-09-10 13:49:53 | 
            
        
            
                | odps-python | 
                0.1.0 | 
                High-performance Python library for Open Data Product Specification (ODPS) v4.0 with caching, validation, and international standards compliance | 
                2025-08-31 08:48:03 | 
            
        
            
                | pystow | 
                0.7.8 | 
                Easily pick a place to store data for your Python code | 
                2025-08-27 13:34:08 | 
            
        
            
                | rust-crate-pipeline | 
                4.0.0 | 
                A comprehensive system for gathering, enriching, and analyzing metadata for Rust crates using AI-powered insights, advanced caching, machine learning predictions, and microservices architecture. | 
                2025-08-26 10:34:08 | 
            
        
            
                | slack-mcp-server | 
                0.2.1 | 
                A Model Context Protocol (MCP) server for Slack workspace integration using FastMCP with robust authentication and caching | 
                2025-08-19 08:40:55 | 
            
        
            
                | cachefuse | 
                0.1.0 | 
                Enterprise-grade caching framework for LLM responses and embeddings | 
                2025-08-18 20:19:38 | 
            
        
            
                | ubelt | 
                1.4.0 | 
                A Python utility belt containing simple tools, a stdlib like feel, and extra batteries | 
                2025-08-17 03:41:35 |