npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

@elefai/n8n-nodes-elefaibrain-memory-lab

v0.1.0-lab.52

Published

Tembory Memory node for n8n AI Agents with profile, tools, timeline, graph and semantic memory

Downloads

6,430

Readme

Tembory Memory

Node de memoria operacional da Tembory para agentes de IA no n8n.

Versao lab atual: 0.1.0-lab.52.

O Tembory entrega contexto rico para o AI Agent sem depender apenas do historico textual da conversa. Ele combina memoria semantica, working memory, decision state, fatos estaveis do lead, historico de tools, estado operacional, action ledger, timeline de entidades, compressao de memoria, grafo, mensagens recentes e diagnosticos.

Smoke tecnico

Antes de publicar uma build lab, rode:

npm run smoke:n8n:multiturn

O smoke simula 12 trocas com tools de agenda, valida tool history, working memory, decision state, memory compression e exige contextHealth com score minimo de 970/1000.

Principais recursos

  • Porta ai_memory para conectar direto no AI Agent do n8n.
  • Campo Projeto para isolar memórias por cliente/workspace mesmo quando a origem repete o mesmo ID de conversa.
  • Entradas opcionais ai_languageModel e ai_embedding para usar os modelos conectados pelo cliente no proprio n8n.
  • Profile facts: nome, empresa, email, telefone, preferencias e contexto comercial.
  • Tool history: quais tools foram chamadas, quando, com qual status e resultado.
  • Tool guard: bloqueia acoes dependentes quando falta contexto previo.
  • Working memory: objetivo atual, intencao recente, entidades ativas, ultimo erro e proxima acao esperada.
  • Decision state: decisoes ativas, ferramentas que nao devem ser repetidas e politica de resolucao de conflitos.
  • Operational state: resumo deterministico do estado atual das tools e do proximo passo seguro.
  • Action ledger: linha cronologica das acoes executadas pelo agente.
  • Entity timeline: evolucao compacta de entidades, fatos, relacoes e eventos relevantes.
  • Memory compression: resumos de turno, sessao, entidades e workflow para reduzir ruido e aproximar o contexto do comportamento do ChatGPT/Codex.
  • Vector memories com scores, recent messages, highlights, graph e resumo.

Custo de IA

O node nao fornece LLM nem embedding gerenciados pela Tembory. Todo uso de LLM e embedding deve vir dos nodes/modelos conectados no cluster do n8n do cliente. O backend do Tembory armazena e consulta os vetores recebidos prontos.

Presets operacionais

O campo avancado Preset Operacional preenche defaults sem sobrescrever valores configurados manualmente:

  • Custom: comportamento manual.
  • Lab: diagnostico completo para teste e auditoria.
  • Producao Balanceada: contexto rico com menos ruido.
  • Producao Economica: reduz secoes e resultados para economizar tokens.
  • Auditoria: payload detalhado para depuracao.

Blocos de contexto

Quando habilitados, o agente recebe:

  • Profile facts
  • Working memory
  • Decision state
  • Operational state
  • Action ledger
  • Entity timeline
  • Memory compression
  • Tool guard
  • Vector memories
  • Graph
  • Recent messages
  • Recent highlights
  • Tool history
  • Diagnostics

Teste local

npm test
npm pack --dry-run

Site: https://tembory.com