In-memory abstract-level database for Node.js and browsers

Simple implmentation of Stream.Readable and Stream.Writable holding the data in memory.

An LRU cache of weak references

Agentic framework for connecting LLMs to messaging platforms, with persistent memory, skills, scheduled tasks, self-healing supervision, and distributed multi-agent collaboration

Verifies email domains

Standalone agent runtime with ReAct loop for AgentsKit.

Chain functions, generators, Node streams, and Web streams into a pipeline with backpressure support.

The Memory Layer For Your AI Apps

The AI-coding operations layer that makes "done" require evidence — persistent memory, evidence-gated completion checks, and clean handoffs for any AI agent (Claude Code, Codex, Cursor). State lives as plain files in your repo. CLI + MCP, 0 runtime depend

This is lightweight memory stream module for node.js.

Local-first unified memory system for AI agents — installs the prebuilt, signature-verified auxly binary.

Per-repo knowledge atlas for agent fleets — verified architecture cards with an honest freshness signal. The past, mapped.

High-performance streaming multipart/mixed parser for Node.js

React for CLI

Session management for TMCP (TypeScript Model Context Protocol) transport implementations. This package provides the base classes and in-memory implementations for both streaming session coordination and session metadata persistence.

A simple key/value storage using files to persist the data

A simple in-memory cache. put(), get() and del()

MongoDB Server for testing (auto-download latest version to ~/.cache/mongodb-binaries).

AI runtime for agent-driven products — agents, memory, LLM providers (Inference Snaps, Ollama, OpenAI-compatible), tools, and orchestration. Anthropic-SDK-free.

In-memory Cache Module for Medusa