DeepSeek LLM prompt-cache hit-rate optimizer for opencode, Claude Code, and Codex CLI.
`BatchLoader` is a tool for batching data requests with support for deduplication, caching, and parallel task management. It is designed to enhance flexibility and performance in scenarios requiring asynchronous data processing. This module was inspired b
Self-hosted LLM gateway and tier-routing proxy for Claude Code, Cursor, and Codex. Routes across Ollama, AWS Bedrock, OpenRouter, Databricks, Azure OpenAI, llama.cpp, and LM Studio with prompt caching, MCP tools, and 60-80% cost savings.
This is a shared ESlint config for åpenhet's projects.
Native bindings for hyperledger indy
NodeJS toolkit for QuickCase
[](https://github.com/rogeriochaves/llm-cost/actions/workflows/node.js.yml) [](https://www.npmjs.com/package/ll
Cache packges deps for lock dep version.
MCP server for AI context optimization — AST-aware code indexing, tiered compaction, FTS5 search, dependency graphs, and LRU caching to minimize token usage.
Local Hyprland Wiki search and retrieval tools for Pi backed by a cloned official hyprland-wiki repository.
Memoization function and decorator.
A REPL to investigate the Parcel graphs in the cache ("offline", after the build).
destroy a stream if possible
Shared client for quikvoice /voice/converse, greeting cache, and offline-safe voice helpers (CLI, desktop, web).
My hunky-dory module
Node.js package for an in-memory NATS server
<div align="right">
Resource-oriented backend framework for Fastify - clean, minimal, powerful, tree-shakable
srv-tool
Claude Code and Codex workflow framework by Qualia Solutions. Plan, build, verify, ship.
Lint faster by only running linters and other tools on files that have recently changed or files that are different from `master` in git.
Convert globs to regular expressions
Redis Cache Module for Medusa
User-friendly glob matching