simple in memory key/value cache with autoclean by timeout

Wontopos — long-term memory for AI agents. Pure semantic retrieval, identical recall in every language, ~100× lower LLM bill.

Parses, serializes, and manipulates MIME types, according to the WHATWG MIME Sniffing Standard

SDK for pyx-memory — Memory as a Service for AI agents

Persistent memory plugin for OpenCode — captures, compresses, and recalls context across coding sessions

``` npm i ofd-view parser_x.js -S ```

Long-term memory engine for AI agents

A in memory time to live cache with streaming support.

Emulate console for all the browsers

A memcache client for node using the binary protocol and SASL authentication

OpenCode plugin for Claude-Mem persistent memory system

mem-cache

Adaptive multi-harness orchestration with seven roles, runtime-autonomous Spec Kit-compatible SDD routes, and external provider boundaries.

Array#isArray for older browsers

A DeepSeek Harness plugin that integrates claude-mem: query, context injection, manual save, and session lifecycle over a local claude-mem worker's HTTP API

Cognitive memory engine for AI agents — episodic, semantic, procedural memory with consolidation

Memory statistics, not provided by `os` module.

Online self-improvement layer for pi. A unified, in-trajectory harness-state store (prompt notes, memory, skill descriptions, sub-agent specs) with a manual /refine that proposes evidence-backed structured CRUD deltas. Composes with pi-reflect (offline) a

Pi-native custom tools for the nmem backend - search memories and threads, read threads, save memories via REST, no CLI

The agentic memory engine — notes that construct, link, and evolve like a Zettelkasten, on Qdrant + Transformers.js. No Python. Framework-agnostic.