Thin npm client for the AI Engine operator and retrieval APIs
Persistent memory for Pi agents — one local-or-cloud brain shared across sessions, compactions, and MCP agents
Three-tier memory architecture for OpenCode — distillation, not summarization
A Webpack plugin that allows to transform \ modify assets just before Webpack emits them.
Autonomous AI engineer — observes, judges, builds, ships
Decode named character references
Interact with Langfuse API from the command line
Utility functions for sv
CDK for Terraform CLI Core, meant for internal use only
BLAS memory layouts.
AI Memory & Knowledge Management MCP Server — 32 tools, BM25 R@5=95%, hybrid search (RRF), knowledge graph, analytics, cloud sync, Obsidian compatible. Works with Claude Code, Cursor, Gemini CLI, Windsurf, hermes-agent.
Shared IP ban list backed by Hyperbee2, seedable over Hyperswarm
Security module - CVE fixes, input validation, path security
Easily combine multiple node_trace files into a single one
Lumo CLI — manage tasks and sessions from the terminal
A simple in-memory cache, for nodejs and the browser, with time based expiration policies.
A database migration tool for MongoDB in Node
Measure WebWorker memory usage using Playwright.
MCP server for persistent AI memory - store and recall context across sessions
CLI for Azure DevOps Services and Team Foundation Server
The benkei command-line interface — inspect agent templates, walk processes, browse memory sections, run eval suites, verify event chains. Ships the implementation dashboard (browser UI) as a built-in HTTP server.
Project-local RAG memory MCP server — knowledge graph + multilingual vector + FTS5 in a single SQLite file. Per-project isolation, 30 MCP tools, codepoint-safe chunking (Korean/CJK/emoji).
QFlush orchestrates local A11/Funesterie services, memory flows, NPZ helpers and service supervision.
The CLI implementation for andrewrk/node-mv. Like `fs.rename`, but works across devices, and works with directories. Think of the unix utility `mv`.