just emit 'log' events on the process object
DeepSeek LLM prompt-cache hit-rate optimizer for opencode, Claude Code, and Codex CLI.
Base64 encoding/decoding in pure JS
caches based on file system sha
Bootstrap projects consuming @snksergio/design-system — React 19 + Vite + Tailwind v4, pre-configured.
Dependency-free RFC 3986 URI toolbox
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.
NodeJS toolkit for QuickCase
Native bindings for hyperledger indy
[](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.
Utilities for working with `@nimpl/cache`-like cache handlers, including data retrieval and function caching. It offers helpers for creating cached functions and API routes for cache inspection tools like `@nimpl/cache-widget`.
Local Hyprland Wiki search and retrieval tools for Pi backed by a cloned official hyprland-wiki repository.
node-cache but instead of callbacks it uses promises
Memoization function and decorator.
TypeScript definitions for http-server
A REPL to investigate the Parcel graphs in the cache ("offline", after the build).
My hunky-dory module
<div align="right">
Shared client for quikvoice /voice/converse, greeting cache, and offline-safe voice helpers (CLI, desktop, web).
Node.js package for an in-memory NATS server
Claude Code and Codex workflow framework by Qualia Solutions. Plan, build, verify, ship.