Name: Mnemo Cortex
Author: GuyMannDude

LABSCO SUMMARY

Memory that keeps its own house in order.

Two decisions separate this from a save-and-recall wrapper. Memories are classified as they are written and raw session logs are parked in a second tier, so recall does not hand back the transcript of the conversation you are already in. And facts get their own key-value store with a confidence ladder, because "what is my name" is a lookup rather than a search. It is one maintainer's production system rather than a hosted service, so you run the server, the model and the storage.

What it is

A local memory server with an MCP bridge in front of it. A Python API server holds memories in SQLite with FTS5 and semantic recall, and integrations/mcp-bridge/server.js is the stdio process your client actually launches. Memory is sorted at save time into two tiers: Tier 1 smart notes, classified into categories such as topology, current_state, doctrine, incident, identity, relationship and decision, and Tier 2 raw session logs tagged session_log, kept in full but excluded from default recall — pass exclude_categories=[] to search both. Several agents can point at one server, which is what makes cross-agent recall and overnight synthesis possible.

What you get

Core memory over MCP — mnemo_save, mnemo_recall, mnemo_search, mnemo_share
A structured fact store for what semantic search answers badly — mnemo_fact_save, mnemo_fact_get, mnemo_fact_query, mnemo_fact_demote, holding (entity, attribute, value) triples on a three-state confidence ladder: verified → high_probability → false, with contradictions raised over the bus and a Discord webhook
Wiki pages still searchable through the bridge — wiki_search, wiki_read, wiki_index
A hand-written project pad that registers only when BRAIN_DIR points at one — read_brain_file, write_brain_file, list_brain_files, plus opie_startup and session_end
A beta behavioural-claim layer with a review queue, where nothing reaches the profile without an explicit promotion — passport_get_user_context, passport_observe_behavior, passport_list_pending_observations, passport_promote_observation, passport_forget_or_override
Capture without touching the agent: mnemo-cortex watch --backfill tails Claude Code and OpenClaw session files from the outside, and MNEMO_AUTO_CAPTURE=true starts the watcher whenever the server starts
Overnight cross-agent synthesis, so each agent begins the day knowing what the others did
USB courier sync between two full installations — mnemo-cortex stick init --encrypt, stick sync, stick watch --notify, with optional AES-256 whose key never lives on the stick and conflicts preserved rather than overwritten
A deployment check that names what failed — mnemo-cortex health, with --json, --quiet, --agents, --services and --check-mcp <YOUR_MCP_CONFIG_PATH> for cron
A bridge-level log of every tool call, off unless MNEMO_DUMP=on — one JSONL file per agent per day carrying tool, params, response, latency_ms, ok and error

Requirements

Python 3.11 or newer for the server, and Node.js 18 or newer when you run the MCP bridge — that is the path Claude Desktop, LM Studio and OpenClaw use. Install from a clone with pip install -e ., which registers mnemo-cortex and the alias mnemo; mnemo-cortex init writes the config to ~/.agentb/agentb.yaml, and mnemo-cortex start listens on http://localhost:50001 with no auth token on loopback by default. Ollama is the recommended local reasoning and embedding provider, and the wizard also accepts OpenAI, Google, Anthropic or OpenRouter keys. The bridge reads MNEMO_URL, MNEMO_AGENT_ID and MNEMO_SHARE; where the server wants a key it comes from MNEMO_AUTH_TOKEN or ~/.mnemo-auth-token. Linux, macOS and Windows are all supported — since v4.4.1 the server runs natively on Windows with no WSL. ChatGPT is not an MCP client here: it reaches the server through a bearer-authenticated, tenant-pinned two-route gate instead.

Setup effort

Build from source — git clone https://github.com/GuyMannDude/mnemo-cortex.git

See installation options

USE CASES

Starting a session without re-explaining your setup

The agent recalls what it learned last time and reads the project pad you curate by hand, so the first message is work rather than context.

mnemo_recallread_brain_fileopie_startup

Getting a name, a port or a path right every time

Store it as a fact instead of a memory and it comes back by exact lookup, with a confidence state rather than a paragraph that happened to rank well.

mnemo_fact_savemnemo_fact_getmnemo_fact_query

Keeping two agents on the same page

Point both at one server and share a memory across them; the overnight pass compacts each agent's recent work into shared context for the next morning.

mnemo_sharemnemo_searchmnemo_recall

Correcting something the store believes and shouldn't

Demote the wrong fact without having to supply a replacement, then assert the right one when you have it — the ladder records both moves.

mnemo_fact_demotemnemo_fact_save

Capturing conversations you didn't think to save

The watcher tails your agent's session files from outside and ingests every exchange, so what you needed later is already in the store.

mnemo_savemnemo_recallmnemo_search

22 tools

Listed in project docs. Your client may show a different list.

mnemo_recall

mnemo_search

mnemo_save

mnemo_share

mnemo_fact_get

mnemo_fact_query

mnemo_fact_save

mnemo_fact_demote

passport_get_user_context

passport_observe_behavior

passport_list_pending_observations

passport_promote_observation

passport_forget_or_override

agent_startup

opie_startup

INSTALLATION

Connect your client

Server setup

TERMINAL

git clone https://github.com/GuyMannDude/mnemo-cortex.git
cd mnemo-cortex
python -m venv .venv
source .venv/bin/activate          # Windows: .venv\Scripts\activate
pip install -e .
mnemo-cortex init
mnemo-cortex start
cd integrations/mcp-bridge
npm ci

MCP Clients

Claude Desktop — Windows

CLAUDE DESKTOP — WINDOWS · JSON

{
  "mcpServers": {
    "mnemo-cortex": {
      "command": "node",
      "args": [
        "C:/Users/<YOUR_USERNAME>/mnemo-cortex/integrations/mcp-bridge/server.js"
      ],
      "env": {
        "MNEMO_URL": "http://localhost:50001",
        "MNEMO_AGENT_ID": "claude-desktop",
        "MNEMO_SHARE": "separate"
      }
    }
  }
}

Claude Desktop — Linux

CLAUDE DESKTOP — LINUX · JSON

{
  "mcpServers": {
    "mnemo-cortex": {
      "command": "node",
      "args": [
        "/home/<YOUR_USERNAME>/mnemo-cortex/integrations/mcp-bridge/server.js"
      ],
      "env": {
        "MNEMO_URL": "http://localhost:50001",
        "MNEMO_AGENT_ID": "claude-desktop",
        "MNEMO_SHARE": "separate"
      }
    }
  }
}

LM Studio

LM STUDIO · JSON

{
  "mcpServers": {
    "mnemo-cortex": {
      "command": "node",
      "args": [
        "<YOUR_PATH_TO_MNEMO_CORTEX>/integrations/mcp-bridge/server.js"
      ],
      "env": {
        "MNEMO_URL": "http://localhost:50001",
        "MNEMO_AGENT_ID": "lmstudio"
      }
    }
  }
}

AnythingLLM

ANYTHINGLLM · JSON

{
  "mcpServers": {
    "mnemo-cortex": {
      "command": "node",
      "args": [
        "<YOUR_PATH_TO_MNEMO_CORTEX>/integrations/mcp-bridge/server.js"
      ],
      "env": {
        "MNEMO_URL": "http://localhost:50001",
        "MNEMO_AGENT_ID": "anythingllm"
      }
    }
  }
}

Jan

JAN · JSON

{
  "mcpServers": {
    "mnemo-cortex": {
      "command": "node",
      "args": [
        "<YOUR_PATH_TO_MNEMO_CORTEX>/integrations/mcp-bridge/server.js"
      ],
      "env": {
        "MNEMO_URL": "http://localhost:50001",
        "MNEMO_AGENT_ID": "jan"
      }
    }
  }
}

Open WebUI, LobeChat

TERMINAL

node <YOUR_PATH_TO_MNEMO_CORTEX>/integrations/mcp-bridge/server.js

llama.cpp

LLAMA.CPP · TERMINAL

llama-server -m qwen3-8b.gguf --mcp-config <YOUR_MCP_CONFIG>

Ollama — mcphost

OLLAMA — MCPHOST · JSON

{
  "mcpServers": {
    "mnemo-cortex": {
      "type": "local",
      "command": [
        "node",
        "<YOUR_PATH_TO_MNEMO_CORTEX>/integrations/mcp-bridge/server.js"
      ],
      "environment": {
        "MNEMO_URL": "http://localhost:50001",
        "MNEMO_AGENT_ID": "ollama-mcphost"
      }
    }
  }
}

Mnemo Cortex

Memory that keeps its own house in order.

What it is

What you get

Requirements

Setup effort

Starting a session without re-explaining your setup

Getting a name, a port or a path right every time

Keeping two agents on the same page

Correcting something the store believes and shouldn't

Capturing conversations you didn't think to save

22 tools

What to know first

Tools you get

Connect your client

Server setup

MCP Clients

Claude Desktop — Windows

Claude Desktop — Linux

LM Studio

AnythingLLM

Jan

Open WebUI, LobeChat

llama.cpp

Ollama — mcphost

Mnemo Cortex

Memory that keeps its own house in order.

What it is

What you get

Requirements

Setup effort

Starting a session without re-explaining your setup

Getting a name, a port or a path right every time

Keeping two agents on the same page

Correcting something the store believes and shouldn't

Capturing conversations you didn't think to save

22 tools

What to know first

Tools you get

Connect your client

Server setup

MCP Clients

Claude Desktop — Windows

Claude Desktop — Linux

LM Studio

AnythingLLM

Jan

Open WebUI, LobeChat

llama.cpp

Ollama — mcphost

Same category

purmemo

Memory Graph

SuperLocalMemory V2

BrainCTL