Showing 1-20 of 98 packages
The time-based use-recency-unaware cousin of [`lru-cache`](http://npm.im/lru-cache)
An enhanced MCP server providing intelligent semantic code search with find-similar-code, recency ranking, and improved chunking. Fork of smart-coding-mcp.
A server that tracks the recency of resources and notifies subscribers of updates
Prune a directory to contain a set number of sub-directories, retention policy is recency
True LRU based on true recency.
Search the web with real-time results and advanced filtering powered by Perplexity's Search API
A Sankey chart built with vega that uses 5 data points from frequency to recency.
list all git objects (in recency order)
Persistent memory for Claude Code - Give Claude a brain that remembers and evolves. Features AIME compression, semantic search, auto-learning, memory evolution, and usefulness tracking.
Smart offline-first JavaScript SDK with intelligent caching for web applications
Dynamic Context Pruning extension for pi - intelligently removes obsolete messages to optimize token usage
Knowledge capture MCP server - remember what you learn with AI
A no dependency javascript runtime key-value cache store for small chunks of arbitrary data (strings, objects, numbers)
A TUI launcher for frequently used commands
In-memory cache with high hit rates via LFU eviction. Supports time-based expiration, automatic loading and metrics.
A hyperbolic least recently used (H-LRU) cache implementation that combines recency and frequency metrics for optimal cache eviction
A neutral SDK that fetches and assembles reputation data from Ethos Network, Talent Protocol, and Neynar (Farcaster) without interpretation, ranking, or judgment.
A powerful CLI tool for the Perplexity AI API - search the web and chat with AI from your terminal
A beautiful web UI for browsing Claude Code conversation history
A Perplexity API Model Context Protocol (MCP) server that unlocks Perplexity's search-augmented AI capabilities for LLM agents. Features robust error handling, secure input validation, and transparent reasoning with the showThinking parameter. Built with