N3MemoryCore Lite (Working Memory) MCP Server

by neuralnexusnote Your server? Claim it

local only

N3MemoryCore Lite (Working Memory) runs on your own machine — the client starts it, so there is no endpoint to ping. 148 installs a week from pypi. Last commit 1 Jun 2026.

Ephemeral 7-day hybrid vector+BM25 working memory, multilingual, backed by Redis Stack.

Installs per day peak 42 · avg 19 · +23% w/w

a month agotoday

148

Installs / week

pypi · n3memorycore-mcp-lite

Stars

0 open issues

1 Jun 2026

Last commit

0 releases in 90 days

Apache-2.0

License

Python

Nothing serious here today

Today is the operative word: we check N3MemoryCore Lite (Working Memory) every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add n3mc-workingmemory -- uvx n3memorycore-mcp-lite

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "n3mc-workingmemory": {
      "args": [
        "n3memorycore-mcp-lite"
      ],
      "command": "uvx"
    }
  }
}

~/.codex/config.toml

[mcp_servers.n3mc-workingmemory]
command = "uvx"
args = ["n3memorycore-mcp-lite"]

.cursor/mcp.json

{
  "mcpServers": {
    "n3mc-workingmemory": {
      "args": [
        "n3memorycore-mcp-lite"
      ],
      "command": "uvx"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "n3mc-workingmemory": {
      "args": [
        "n3memorycore-mcp-lite"
      ],
      "command": "uvx"
    }
  }
}

Alternatives to N3MemoryCore Lite (Working Memory)

same job, measured the same way

Vector Memory

by neerajg03

Semantic document memory using Redis vector store. Save and recall files with natural language.

205 installs/wk local only

Fusionpact Vectordb

by atul-fusionpact

Hybrid vector + reasoning retrieval, agent memory, multi-agent orchestration, MCP server, and RAG.

35 installs/wk local only

Memtomem

by memtomem

Markdown-first long-term memory for AI agents. Hybrid BM25 + vector search, runs locally.

local only

SmartMemory

by smartmemory

Graph + vector memory for agents: recall, ingest, search, distill. Local or remote backend.

1 640 installs/wk local only

Code Index

by achreftlili

SQLite-backed hybrid (vector + FTS) code search index for Claude Code over MCP.

213 installs/wk local only

Clude

by sebbsssss

Portable agent memory anchored on Solana. Local SQLite + vector recall, open export.

74 installs/wk local only

Hindsight MemPalace

by holetron

Self-hosted long-term memory for AI agents over MCP — hierarchical recall backed by pgvector

21 installs/wk local only

Memory Vault

by mihaibuilds

Local-first AI memory layer with hybrid search. Postgres + pgvector. Self-hosted, MIT.

local only

N3MemoryCore Lite (Working Memory) — questions

Answers built from our own checks of this server.

Why is there no uptime for N3MemoryCore Lite (Working Memory)?

N3MemoryCore Lite (Working Memory) runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package n3memorycore-mcp-lite was installed 148 times last week.

How do I connect N3MemoryCore Lite (Working Memory)?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It runs locally, so the command pulls n3memorycore-mcp-lite straight from pypi; nothing to host, nothing to sign up for.

How many people use N3MemoryCore Lite (Working Memory)?

The pypi package n3memorycore-mcp-lite was installed 148 times in the last week. Week over week that is +23%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is N3MemoryCore Lite (Working Memory) open source?

Yes — it is published under the Apache-2.0 licence, written in Python and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.