ZenBrain Memory

ai.zensationPublished by zensation.aiv0.3.1Updated Nov 3, 2026

Agent memory: working, episodic, semantic, procedural and core layers. Local SQLite, no account.

The publisher's own server: Memory.fit

VerifiedSTDIODesktop onlyDatabasesKnowledge & Memory

Overview

AI-generated overview

Local MCP server that gives an assistant a persistent, layered long-term memory stored in a single SQLite file, with no account or network calls.

What you can do
  • Store new memories, with automatic routing into procedural, episodic, semantic or core layers
  • Search memory across layers by query, with scored results and ids
  • Delete a memory permanently by id and layer, including what consolidation linked to it
  • Run a consolidation pass that turns emotionally weighted episodes into facts and decays working memory
  • Check how full each memory layer is with a read-only health report
When to use it
Useful when you want an assistant to remember facts, procedures and past episodes across separate conversations on one machine, without a hosted memory service. Suited to single-user, local setups where a plain file is an acceptable store.
Requirements
Node.js 22 or newer; installed as the npm package @zensation/mcp and run locally over stdio. Set ZENBRAIN_DB to an absolute or ~/ path for the SQLite file, since a relative path may resolve to a directory the client cannot write to. No account, API key or network access is needed.
Before you install
The SQLite store is a plain, unencrypted file, so place it where you would keep a notebook. zenbrain_forget permanently deletes a memory and what consolidation linked to it, and cannot be undone; zenbrain_consolidate is also marked destructive because it removes decayed working-memory slots. Recall is lexical rather than semantic unless an embedding provider is configured in the library.

Installation

In SourceWeft

  1. Open ZenBrain Memory in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

@zensation/mcp

Status: early release. The tool surface is small on purpose and may still change before 1.0. The memory layers underneath it are the same ones the ZenBrain paper describes and the benchmarks measure.

An MCP server that gives any MCP client — Claude Desktop, Claude Code, Cursor, or your own — a memory that survives the conversation.

Five tools, one local SQLite file, no account and no network call.

ToolWhat it does
zenbrain_storeWrite something into long-term memory. Routing is automatic, first match wins: steps or wording such as "How to", "Steps:", "workflow:" make a procedure, an emotional weight above 0.5 an episode, a confidence above 0.9 a pinned core memory, anything else a semantic fact. Each call adds a memory; the same core memory stored again is updated.
zenbrain_recallSearch the episodic, semantic, procedural and core layers for what is relevant to a query; working memory only when you name it. Results come back sorted by a score from 0 to 1, each with its id and the layer it came from; a layer in which nothing matches returns recent episodes and facts, or its most successful procedures, at score 0, behind every hit, and minScore above 0 leaves them out. Every core block scores 0.5 or 0.8.
zenbrain_forgetDelete a memory for good, by the id and layer zenbrain_recall returned, together with what consolidation linked to it: forgetting an episode deletes the fact made from it, forgetting such a fact every episode consolidated into it, and both delete the working-memory copies of that content. alsoForgotten lists what went with it. A memory stored on its own and never consolidated keeps its long-term entry (duplicates on a recall result names such copies); forget a long-term result rather than a working-memory slot, which is only a copy. To correct a memory, forget it and store the corrected version.
zenbrain_consolidateOne maintenance pass: among the 100 most recent episodes, each with an emotional weight above 0.5 becomes a semantic fact, only once; working-memory slots decay, and those at a relevance of 0.01 or below are removed. Deletes nothing from long-term memory.
zenbrain_healthHow full each layer is: slots in use, episodes, facts and how many are due for review, procedures, core blocks.

Each tool also tells the client what it does to the store, through the MCP tool annotations: zenbrain_recall and zenbrain_health are read-only; zenbrain_store only adds; zenbrain_forget and zenbrain_consolidate are marked destructive (consolidation removes decayed working-memory slots), so a client that asks before destructive calls asks before these two. No tool reaches anything outside the local file.

Install

Requires Node.js 22 or newer.

bash
npm install -g @zensation/mcp

Configure your client

json
{  "mcpServers": {    "zenbrain": {      "command": "npx",      "args": ["-y", "@zensation/mcp"],      "env": {        "ZENBRAIN_DB": "~/.zenbrain/memory.db"      }    }  }}
VariableDefaultMeaning
ZENBRAIN_DB./zenbrain.dbPath to the SQLite file. A leading ~/ means your home directory. A relative path is relative to the directory your client starts the server in — some clients, Claude Desktop among them, may start it in /, where nothing can be written — so give an absolute or ~/ path. :memory: gives a store that is discarded when the process exits. A value that is only an unfilled placeholder such as ${user_config.db_path}, which a host may pass on when it does not fill in plugin settings, counts as ~/.zenbrain/memory.db; the server says so on stderr.
ZENBRAIN_CONTEXTSpersonal,work,learning,creativeComma-separated context domains, passed to the cross-context layer. None of the five tools uses that layer yet, so the value currently has no effect.

The server speaks MCP over stdio. Stdout carries protocol traffic only; diagnostics go to stderr.

In Claude Code, one line does the same with the memory in ~/.zenbrain/memory.db:

bash
claude mcp add --scope user zenbrain -e ZENBRAIN_DB=~/.zenbrain/memory.db -- npx -y @zensation/mcp

or install the Claude Code plugin, which runs this server at a pinned version, keeps the memory in the same file and lets you choose another (db_path):

bash
claude plugin install zenbrain --marketplace zensation-ai/zenbrain

The seven layers

Storing is not filing. Which layer a memory lands in decides how it is retrieved and what consolidation does with it. The five tools reach working, episodic, semantic, procedural and core memory; short-term memory shows up only as a counter in zenbrain_health, and cross-context memory is not wired to any tool.

LayerHolds
7Cross-Context MemoryLinks between entities of different domains (experimental; no tool uses it)
6Core MemoryPinned facts
5Procedural Memory"How to do X" — skills and workflows
4Long-Term SemanticFacts, with FSRS-style scheduling
3Episodic MemoryConcrete experiences and events
2Short-Term / SessionCurrent conversation context
1Working MemoryActive task focus, 7±2 items

Nothing in long-term memory decays or is deleted on its own; only working memory decays. Every fact gets an FSRS-style review schedule, but no tool reports a review, so through this server the schedule is not advanced. Emotional weight decides routing (above 0.5: an episode) and which episodes consolidation turns into facts. The algorithms are in @zensation/algorithms and can be read line by line.

This server configures no LLM provider, so nothing in it calls a model: routing on store is a content heuristic, and consolidation runs without generated summaries.

What this release does not do

Worth knowing before you wire it in:

  • No embedding provider is configured by default, so recall is lexical, not semantic. Without vectors, recall ranks by folded token overlap — umlauts and accents are folded, rarer words weigh more, and an adjacent phrase beats the same words scattered. It will find "Kieler Foerde" in a note about the "Kieler Förde"; it will not connect "car" to "automobile". Episodes and facts are ranked over the most recent 500 of each, procedures over the 500 with the highest success rate. A layer in which the query matches nothing returns its most recent episodes and facts, or its most successful procedures, at score: 0, behind every hit; every core block comes with 0.5 or 0.8, so a block can rank above a weak hit. Working memory, when you ask for it, is ranked the same way. Pass an EmbeddingProvider through the library for true semantic matching — that is the configuration the published benchmarks were measured with.
  • SQLite similarity search is a full scan. Fine for one person's memory; use @zensation/adapter-postgres for larger volumes.
  • Consolidation is a tool call, not a schedule. Nothing runs it for you.
  • The store is a plain file. It is not encrypted. Put it somewhere you would put a notebook. While the server runs, SQLite keeps -wal and -shm files next to it.

Using it as a library

The server factory is exported, so you can mount ZenBrain's tools on a server of your own or drive them in tests. The package is ESM; require() loads it on Node 22.12 and later (on 22.0–22.11, use import).

typescript
import { createZenBrainServer } from '@zensation/mcp/server';import { MemoryCoordinator } from '@zensation/core';import { SqliteAdapter } from '@zensation/adapter-sqlite';
const coordinator = new MemoryCoordinator({  storage: new SqliteAdapter({ filename: './memory.db' }),});
const server = createZenBrainServer(coordinator);// connect it to any transport you like — the caller owns the coordinator's lifecycle

Zero-dependency, and where that stops

@zensation/algorithms and @zensation/core pull nothing but each other. That claim is checked in CI on every push against the packed tarballs, not against the source tree.

This package is deliberately outside that boundary. An MCP server needs the protocol SDK, so it carries one. Keeping it in its own package is what lets the core stay clean: installing @zensation/core never pulls the MCP SDK, and installing this never weakens the claim the core makes.

About ZenBrain

ZenBrain is a seven-layer, neuroscience-derived memory architecture for LLM agents, built in TypeScript and published under Apache-2.0; @zensation/algorithms and @zensation/core have no third-party dependencies. The benchmark results, and the configuration they were measured in, are reported in the paper; the reproduction packages are on Zenodo.

Works out of the box without an embedding provider — lexical ranking, nothing extra to install. In the paper, ZenBrain's benchmark runs against other systems used nomic-embed-text as the embedding provider; the retrieval ablations used OpenAI text-embedding-3-small.

License: Apache-2.0

Source: packages/mcp/README.md at commit 937b091

Tools

5

zenbrain_store

Store a memory

Write something into long-term memory so it survives this conversation. Routing is automatic by default, first match wins: `steps`, or wording such as "How to", "Steps:" or "workflow:", make a procedure; an emotional weight above 0.5 (detected, or set via `emotionalWeight`) an episode; a `confidence` above 0.9 a pinned core memory; anything else a semantic fact. Set `type` only when you want to override that. Every call adds a new memory, except that storing the same core memory again updates it; the content is also kept in working memory (the most recent seven) while the server runs, so once seven are held each store replaces the oldest copy there. Long-term memory is never changed by a store. Returns the id of the stored memory. If it may already be stored, check with zenbrain_recall first: storing it again adds a duplicate.

ParameterstypestepstoolssourcecontentrequiredcontextoutcomeconfidenceemotionalWeight

zenbrain_recall

Recall memories

Search long-term memory for anything relevant to a query. By default it searches the episodic, semantic, procedural and core layers; working memory (the most recent stores, held only while the server runs, up to five results) is searched only when named in `layers`. Returns results sorted by score, each with its id and the layer it came from; zenbrain_forget takes both. The score runs from 0 to 1 and says how well a result matches the query; a layer in which nothing matches returns recent memories (or its most successful procedures) at 0, behind every hit, and minScore above 0 leaves them out. Every core block scores 0.5 or 0.8, so a block can rank above a weak hit. Use this before answering when the user refers to something from an earlier session. To see how much is stored rather than what, use zenbrain_health; to save something, use zenbrain_store.

ParameterslimitqueryrequiredlayersminScoreminConfidence

zenbrain_forget

Forget a memory

Permanently delete a memory, addressed by the id and layer that zenbrain_recall returned for it, together with what consolidation linked to it; this cannot be undone. Forgetting an episode also deletes the fact zenbrain_consolidate made from it; forgetting such a fact also deletes every episode consolidated into it; both also delete the working-memory copies of that content. Forgetting a working-memory result deletes only that copy. alsoForgotten lists everything deleted besides the memory itself. A memory stored on its own and never consolidated keeps its long-term entry. Use it when the user asks to forget something or a stored memory is wrong; to correct a memory, forget it and store the corrected version with zenbrain_store. An id the layer does not hold is reported as not forgotten, not as an error.

Parametersidrequiredlayerrequired

zenbrain_consolidate

Consolidate memory

Run one consolidation pass: among the 100 most recent episodes, each one with an emotional weight above 0.5 becomes a semantic fact — once, however often the pass runs. Working-memory slots lose relevance with age, and slots whose relevance has dropped to 0.01 or below are removed; that is the only deletion, and nothing in long-term memory is deleted. Run it between sessions or after a batch of zenbrain_store calls, not on every turn; compare zenbrain_health before and after to see the effect.

Takes no parameters.

zenbrain_health

Inspect memory state

Report how full the memory layers are: working-memory slots in use, interactions held, episodes, facts and how many are due for review, procedures, core blocks. Read-only and cheap, safe to call at any time. It returns counts only; to read the memories themselves, use zenbrain_recall.

Takes no parameters.

Version history

10
  1. v0.3.1LatestOct 31, 2026
  2. v0.3.0Oct 17, 2026
  3. v0.2.2Oct 16, 2026
  4. v0.2.1Oct 11, 2026
  5. v0.2.0Oct 10, 2026
  6. v0.1.9Oct 1, 2026
  7. v0.1.8Oct 1, 2026
  8. v0.1.7Sep 30, 2026
  9. v0.1.6Sep 27, 2026
  10. v0.1.3Sep 16, 2026

Score

90% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts
  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

Other Memory integrations

Memory.fit

fit.memoryOfficial publisher

Hosted Memory.fit server that lets an AI read your training, sleep, recovery and nutrition data and write back weekly plans, targets and meal plans.

Streamable HTTPWeb executableAuth
Location & LifestyleCredential requiredOct 29, 2026

pg.ddx.io: the PostgreSQL community's memory

io.ddx.pgOfficial publisher

pg.ddx.io: the PostgreSQL community's memory's hosted MCP server, published by pg.ddx.io; no sign-in required; Streamable HTTP; 29 tools.

Streamable HTTPWeb executable
Databases29 toolsOct 24, 2026

var.gg Naming Memory

gg.varOfficial publisher

Remote MCP server that suggests and searches code identifier names from domain concepts in Korean, Japanese, Chinese, Vietnamese and English, and exposes ERD…

Streamable HTTPWeb executable
Databases7 toolsOct 27, 2026

Counterparts

ai.counterparts

Local-first long-term memory for Claude Code and Claude Desktop: the assistant writes notes about you and your projects and recalls them in later sessions.

STDIODesktop only
AI & MLNot validated yetNov 7, 2026

LAHZE - Persian AI Memory Platform

Published by GitHub account pedramgholizadeh

LAHZE - Persian AI Memory Platform's hosted MCP server; no sign-in required; Streamable HTTP; 13 tools.

Streamable HTTPWeb executable
Location & Lifestyle13 toolsNov 3, 2026