Wisdomgraph

Neo4j-native DIKW memory for Claude Code — knowledge that compounds across sessions

Quick Install

Automated & IDE Setup

Copy the AI prompt to install this server into Claude Code, Cursor, or another agent — or use 1-click editor setup below.

Add to Cursor Add to VS Code

Manual Client & Custom JSON ConfigExpand JSON ▾

Client Config & Setup

Choose your client or environment

Target File:~/Library/Application Support/Claude/claude_desktop_config.json

claude_desktop_config.json

{
  "mcpServers": {
    "wisdomgraph": {
      "command": "npx",
      "args": [
        "-y",
        "wisdomgraph"
      ]
    }
  }
}

💡 Paste the JSON block into your client's configuration file under mcpServers, then restart the application.

Documentation Overview

wisdomGraph

English | 简体中文

Graph-native persistent cognition for AI agents.

graphify gives you a snapshot. wisdomGraph gives you memory that compounds.

Use wisdomGraph from Claude Code, Codex, OpenClaw, or any MCP host. Feed it your codebases, notes, papers, conversations — every run merges into a living Neo4j graph. The graph doesn't reset. It accumulates. Facts become patterns. Patterns become insights. Insights become wisdom.

Code

/wisdom .                      # absorb this project into the wisdom graph
/wisdom ask "what patterns repeat across all my projects?"
/wisdom reflect                # promote insights → wisdom, close the feedback loop

The step function over graphify

graphify is excellent at what it does: turn a folder into a knowledge graph snapshot. One run, one graph.json, one GRAPH_REPORT.md. Read it. Next session, start over.

wisdomGraph does something fundamentally different.

	graphify	wisdomGraph
Storage	`graph.json` file (per-project)	Neo4j (persistent, all projects)
Node types	flat (code entities, concepts)	typed DIKW: Knowledge / Experience / Insight / Wisdom
Runs	snapshot, overwrites	MERGE — each run grows the graph
Query	read GRAPH_REPORT.md	live Cypher traversal at inference time
Memory	resets each session	accumulates across sessions, projects, months
Reasoning	community detection (topology)	graph path traversal + DIKW hierarchy
Feedback loop	none	Wisdom → Knowledge (neuroplasticity)
Database	none required	Neo4j Aura (free) or local Neo4j Docker

The difference is not incremental. It's architectural. graphify compresses a codebase into a readable report. wisdomGraph builds an artificial epistemology — one that remembers, connects, and grows.

The DIKW pyramid, operationalized

Human experts don't store flat facts. They organize experience into layers:

Code

Wisdom    ← actionable principles derived from patterns
  ↑
Insight   ← patterns detected across multiple experiences
  ↑
Experience ← events, decisions, outcomes with context
  ↑
Knowledge ← verified facts, documented behaviors, extracted structure

Every node in the wisdomGraph carries a tier label. The graph topology is the cognitive architecture. When you ask a question, Cypher traverses upward through the tiers — not keyword-matching flat text, but reasoning across lived experience.

The feedback loop is critical: when a Wisdom node is queried and found useful, it reinforces connected Knowledge nodes. The graph learns what matters.

Install

Requires: Python 3.10+ and one of: Claude Code, Codex, OpenClaw, or another MCP host

And one of: Neo4j Aura Free (cloud, no install) or Docker Desktop/Engine for a managed local Neo4j container

Terminal

pip install 'wisdomgraph[mcp]'
wisdom quickstart

wisdom quickstart is the end-to-end first-time setup. It prepares storage, verifies the Neo4j connection, and registers wisdomGraph with detected MCP hosts.

bash

# Local managed Neo4j backend + detected MCP hosts
wisdom quickstart

# Local backend + Codex only
wisdom quickstart --host codex

# Existing Neo4j or DozerDB instance
wisdom quickstart --storage existing --uri bolt://localhost:7689 --user neo4j --password <password>

# Neo4j Aura
wisdom quickstart --storage aura --uri bolt+s://xxxxxxxx.databases.neo4j.io --user neo4j --password <password>

The MCP server itself never starts Docker or creates databases. Storage setup is explicit through quickstart, local, docker, or connect.

Option A — Managed local backend (recommended first run)

bash

wisdom local up
wisdom doctor

This starts a managed neo4j:latest container named wisdomgraph-neo4j, stores data under ~/.wisdom/neo4j, uses the documented local login neo4j/password, saves the connection, and leaves MCP startup cleanly separate. The implementation uses the Docker CLI directly, so the same wisdom local up command works from Windows PowerShell, Windows cmd.exe, macOS Terminal, and Ubuntu Terminal after Docker is installed.

Useful commands:

bash

wisdom local status
wisdom local logs
wisdom local down

Option B — Neo4j Aura (zero local database)

Create a free account at neo4j.com/cloud/aura
Create a free AuraDB instance — copy the connection URI and password
Run:

bash

wisdom connect bolt+s://xxxxxxxx.databases.neo4j.io --user neo4j --password <your-password>

Free tier: 200,000 nodes. Enough for years of accumulated wisdom.

Option C — Optional/manual DozerDB Docker (full control, APOC included)

bash

wisdom docker up        # pulls graphstack/dozerdb:5.26.3.0 and starts it
wisdom connect bolt://localhost:7687 --user neo4j --password password

Or manually:

Terminal

docker run -d \
  -p 7474:7474 -p 7687:7687 \
  -v $HOME/neo4j-wisdom/data:/data \
  -v $HOME/neo4j-wisdom/logs:/logs \
  --env NEO4J_AUTH=neo4j/password \
  --env NEO4J_PLUGINS='["apoc"]' \
  graphstack/dozerdb:5.26.3.0

Open localhost:7474 — Neo4j Browser is your visual window into the wisdom graph.

Platform support

Platform	Install command
Claude Code (Linux/Mac)	`wisdom install`
Claude Code MCP	`wisdom mcp-install`
Codex MCP	`wisdom mcp-install --host codex`
Claude Code (Windows)	`wisdom install --platform windows`
OpenClaw	`wisdom install --platform claw`

Then open your AI coding assistant and type:

Code

/wisdom .

MCP integration (v0.2.0+)

wisdomGraph ships as a native Model Context Protocol (MCP) server. Once registered, Claude, Codex, or another MCP host can call wisdomGraph tools directly — no /wisdom slash command needed.

Claude Code setup

bash

wisdom mcp-install

This writes the MCP server entry to .claude/settings.json in your current project:

config.json

{
  "mcpServers": {
    "wisdomGraph": {
      "command": "wisdom",
      "args": ["mcp"]
    }
  }
}

Restart Claude Code. wisdomGraph is now live in that project.

Codex setup (v0.3.0+)

bash

wisdom mcp-install --host codex

This runs the Codex MCP registration:

bash

codex mcp add wisdomGraph -- wisdom mcp

Start a new Codex session. Codex can now launch wisdom mcp and use the same Neo4j-backed DIKW graph as Claude Code.

MCP tools

Tool	What agents use it for
`wisdom_ingest`	Absorb a file, directory, or URL into Neo4j
`wisdom_remember`	Store a fact, decision, or insight explicitly
`wisdom_learn`	Record an attempt, outcome, and lesson learned
`wisdom_status`	Read DIKW tier counts and edge/source totals
`wisdom_list`	List nodes by DIKW tier, project, and connectivity
`wisdom_trace`	Trace why an insight or wisdom node exists
`wisdom_explain`	Explain a node with its DIKW chain and sources
`wisdom_query`	Run a read-only Cypher traversal
`wisdom_reflect`	Trigger DIKW promotion pipeline
`wisdom_report`	Get tier counts + top Wisdom nodes as markdown

Example — Claude remembering across sessions

Session 1:

Claude calls wisdom_remember with label "DozerDB ignores NEO4J_AUTH if data dir exists", tier experience.

Session 2 (days later, fresh terminal):

You ask "how do I reset DozerDB credentials?" Claude calls wisdom_query → finds the Experience node → answers from your own history.

The graph remembered. Claude didn't forget.

Global vs project MCP install

bash

# Register for the current project only
wisdom mcp-install

# Register globally (all projects on this machine)
wisdom mcp-install --project ~

# Register globally with Codex
wisdom mcp-install --host codex

Usage

Code

/wisdom                              # absorb current directory
/wisdom ./raw                        # absorb a specific folder
/wisdom ./raw --mode deep            # aggressive INFERRED edge extraction
/wisdom ./raw --update               # re-absorb only changed files, MERGE into graph
/wisdom ./raw --tier knowledge       # force all extractions into Knowledge tier only

/wisdom add https://arxiv.org/abs/1706.03762   # absorb a paper
/wisdom add https://x.com/...                  # absorb a tweet thread
/wisdom add https://...  --author "Name"        # tag the source author

/wisdom ask "what patterns repeat across all my projects?"
/wisdom ask "what do I know about authentication flows?"
/wisdom ask "trace the path from attention to optimizer"
/wisdom ask "..." --tier wisdom      # only traverse Wisdom-tier nodes in answer

/wisdom reflect                      # LLM promotion pass: Knowledge→Experience→Insight→Wisdom
/wisdom reflect --project ./raw      # reflect only on nodes from this corpus

/wisdom path "DigestAuth" "OAuth"    # shortest path between two concepts
/wisdom explain "CausalSelfAttention"  # full DIKW context for a node
/wisdom god-nodes                    # highest-degree concepts across all projects

Read the full README →View source on GitHub →

Related MCP Servers

View all in Knowledge & Memory View all alternatives

Reviews

No reviews yet — be the first to share how this listing worked for you.

Frequently Asked Questions about Wisdomgraph

Add the following block to your claude_desktop_config.json under mcpServers: "mcpServers": { "wisdomgraph": { "command": "npx", "args": ["-y", "wisdomgraph"] } }

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:

Live Dynamic SVG Preview

Markdown (GitHub README)

[![AllMCPs](https://allmcps.com/api/badge/wisdomgraph?style=directory)](https://allmcps.com/mcp/wisdomgraph)

HTML Embed

<a href="https://allmcps.com/mcp/wisdomgraph"><img src="https://allmcps.com/api/badge/wisdomgraph?style=directory" alt="Wisdomgraph on AllMCPs" /></a>

Technical Specs & Signals

CategoryKnowledge & Memory

27Quality signal: Emerging · 27/100How this signal is calculated ▾

Server availabilityNot measured

Not scored for repo-hosted servers — we can't reach the running server, only its GitHub page. Hosted MCP endpoints are health-checked live.

Verified ownership8/20

Documentation & tools11/30

Adoption & activity1/15

Community engagement0/10

A guidance signal from public completeness & health data — not a user rating. New listings start lower and rise as they add docs, get verified, and grow adoption. Signals we can't observe for a listing are skipped, not counted against it.

★ Featured

AllMCPs Server

The official MCP server for AllMCPs.com - submit and manage tools directly from your AI. The open directory for MCP servers. Connect Claude, Cursor, Windsurf, and AI agents to databases, tools, files, and APIs. Explore 10,000+ servers. AllMCPs is the premier, open directory for discovering, evaluating, and installing Model Context Protocol (MCP) servers to equip AI agents and LLMs with real-world superpowers.

Explore Server →

Own this project?

This directory is pre-filled from public sources. Claim via GitHub README, site badge, or DNS TXT to unlock edit access and the Official badge and attach your website — proof is checked automatically, then reviewed by our team.

Free dofollow backlink: add your website and place the AllMCPs badge on it — no claim needed. We detect it automatically and keep it verified as long as the badge stays live.

Claim & get free dofollow

Share & Embed

Add our SVG badge (dark/light directory styles) or embeddable widget to your site.

Explore more

More in 🧠 Knowledge & Memory →Best MCP servers for Memory & Knowledge →Alternatives to Wisdomgraph →Install in Claude Desktop Install in Cursor Install in VS Code

Wisdomgraph

Neo4j-native DIKW memory for Claude Code — knowledge that compounds across sessions

Quick Install

Automated & IDE Setup

Copy the AI prompt to install this server into Claude Code, Cursor, or another agent — or use 1-click editor setup below.

Add to Cursor Add to VS Code

Manual Client & Custom JSON ConfigExpand JSON ▾

Client Config & Setup

Choose your client or environment

Target File:~/Library/Application Support/Claude/claude_desktop_config.json

claude_desktop_config.json

{
  "mcpServers": {
    "wisdomgraph": {
      "command": "npx",
      "args": [
        "-y",
        "wisdomgraph"
      ]
    }
  }
}

💡 Paste the JSON block into your client's configuration file under mcpServers, then restart the application.

Documentation Overview

wisdomGraph

English | 简体中文

Graph-native persistent cognition for AI agents.

graphify gives you a snapshot. wisdomGraph gives you memory that compounds.

Code

/wisdom .                      # absorb this project into the wisdom graph
/wisdom ask "what patterns repeat across all my projects?"
/wisdom reflect                # promote insights → wisdom, close the feedback loop

The step function over graphify

graphify is excellent at what it does: turn a folder into a knowledge graph snapshot. One run, one graph.json, one GRAPH_REPORT.md. Read it. Next session, start over.

wisdomGraph does something fundamentally different.

	graphify	wisdomGraph
Storage	`graph.json` file (per-project)	Neo4j (persistent, all projects)
Node types	flat (code entities, concepts)	typed DIKW: Knowledge / Experience / Insight / Wisdom
Runs	snapshot, overwrites	MERGE — each run grows the graph
Query	read GRAPH_REPORT.md	live Cypher traversal at inference time
Memory	resets each session	accumulates across sessions, projects, months
Reasoning	community detection (topology)	graph path traversal + DIKW hierarchy
Feedback loop	none	Wisdom → Knowledge (neuroplasticity)
Database	none required	Neo4j Aura (free) or local Neo4j Docker

The DIKW pyramid, operationalized

Human experts don't store flat facts. They organize experience into layers:

Code

Wisdom    ← actionable principles derived from patterns
  ↑
Insight   ← patterns detected across multiple experiences
  ↑
Experience ← events, decisions, outcomes with context
  ↑
Knowledge ← verified facts, documented behaviors, extracted structure

The feedback loop is critical: when a Wisdom node is queried and found useful, it reinforces connected Knowledge nodes. The graph learns what matters.

Install

Requires: Python 3.10+ and one of: Claude Code, Codex, OpenClaw, or another MCP host

And one of: Neo4j Aura Free (cloud, no install) or Docker Desktop/Engine for a managed local Neo4j container

Terminal

pip install 'wisdomgraph[mcp]'
wisdom quickstart

wisdom quickstart is the end-to-end first-time setup. It prepares storage, verifies the Neo4j connection, and registers wisdomGraph with detected MCP hosts.

bash

# Local managed Neo4j backend + detected MCP hosts
wisdom quickstart

# Local backend + Codex only
wisdom quickstart --host codex

# Existing Neo4j or DozerDB instance
wisdom quickstart --storage existing --uri bolt://localhost:7689 --user neo4j --password <password>

# Neo4j Aura
wisdom quickstart --storage aura --uri bolt+s://xxxxxxxx.databases.neo4j.io --user neo4j --password <password>

The MCP server itself never starts Docker or creates databases. Storage setup is explicit through quickstart, local, docker, or connect.

Option A — Managed local backend (recommended first run)

bash

wisdom local up
wisdom doctor

Useful commands:

bash

wisdom local status
wisdom local logs
wisdom local down

Option B — Neo4j Aura (zero local database)

Create a free account at neo4j.com/cloud/aura
Create a free AuraDB instance — copy the connection URI and password
Run:

bash

wisdom connect bolt+s://xxxxxxxx.databases.neo4j.io --user neo4j --password <your-password>

Free tier: 200,000 nodes. Enough for years of accumulated wisdom.

Option C — Optional/manual DozerDB Docker (full control, APOC included)

bash

wisdom docker up        # pulls graphstack/dozerdb:5.26.3.0 and starts it
wisdom connect bolt://localhost:7687 --user neo4j --password password

Or manually:

Terminal

docker run -d \
  -p 7474:7474 -p 7687:7687 \
  -v $HOME/neo4j-wisdom/data:/data \
  -v $HOME/neo4j-wisdom/logs:/logs \
  --env NEO4J_AUTH=neo4j/password \
  --env NEO4J_PLUGINS='["apoc"]' \
  graphstack/dozerdb:5.26.3.0

Open localhost:7474 — Neo4j Browser is your visual window into the wisdom graph.

Platform support

Platform	Install command
Claude Code (Linux/Mac)	`wisdom install`
Claude Code MCP	`wisdom mcp-install`
Codex MCP	`wisdom mcp-install --host codex`
Claude Code (Windows)	`wisdom install --platform windows`
OpenClaw	`wisdom install --platform claw`

Then open your AI coding assistant and type:

Code

/wisdom .

MCP integration (v0.2.0+)

wisdomGraph ships as a native Model Context Protocol (MCP) server. Once registered, Claude, Codex, or another MCP host can call wisdomGraph tools directly — no /wisdom slash command needed.

Claude Code setup

bash

wisdom mcp-install

This writes the MCP server entry to .claude/settings.json in your current project:

config.json

{
  "mcpServers": {
    "wisdomGraph": {
      "command": "wisdom",
      "args": ["mcp"]
    }
  }
}

Restart Claude Code. wisdomGraph is now live in that project.

Codex setup (v0.3.0+)

bash

wisdom mcp-install --host codex

This runs the Codex MCP registration:

bash

codex mcp add wisdomGraph -- wisdom mcp

Start a new Codex session. Codex can now launch wisdom mcp and use the same Neo4j-backed DIKW graph as Claude Code.

MCP tools

Tool	What agents use it for
`wisdom_ingest`	Absorb a file, directory, or URL into Neo4j
`wisdom_remember`	Store a fact, decision, or insight explicitly
`wisdom_learn`	Record an attempt, outcome, and lesson learned
`wisdom_status`	Read DIKW tier counts and edge/source totals
`wisdom_list`	List nodes by DIKW tier, project, and connectivity
`wisdom_trace`	Trace why an insight or wisdom node exists
`wisdom_explain`	Explain a node with its DIKW chain and sources
`wisdom_query`	Run a read-only Cypher traversal
`wisdom_reflect`	Trigger DIKW promotion pipeline
`wisdom_report`	Get tier counts + top Wisdom nodes as markdown

Example — Claude remembering across sessions

Session 1:

Claude calls wisdom_remember with label "DozerDB ignores NEO4J_AUTH if data dir exists", tier experience.

Session 2 (days later, fresh terminal):

You ask "how do I reset DozerDB credentials?" Claude calls wisdom_query → finds the Experience node → answers from your own history.

The graph remembered. Claude didn't forget.

Global vs project MCP install

bash

# Register for the current project only
wisdom mcp-install

# Register globally (all projects on this machine)
wisdom mcp-install --project ~

# Register globally with Codex
wisdom mcp-install --host codex

Usage

Code

/wisdom                              # absorb current directory
/wisdom ./raw                        # absorb a specific folder
/wisdom ./raw --mode deep            # aggressive INFERRED edge extraction
/wisdom ./raw --update               # re-absorb only changed files, MERGE into graph
/wisdom ./raw --tier knowledge       # force all extractions into Knowledge tier only

/wisdom add https://arxiv.org/abs/1706.03762   # absorb a paper
/wisdom add https://x.com/...                  # absorb a tweet thread
/wisdom add https://...  --author "Name"        # tag the source author

/wisdom ask "what patterns repeat across all my projects?"
/wisdom ask "what do I know about authentication flows?"
/wisdom ask "trace the path from attention to optimizer"
/wisdom ask "..." --tier wisdom      # only traverse Wisdom-tier nodes in answer

/wisdom reflect                      # LLM promotion pass: Knowledge→Experience→Insight→Wisdom
/wisdom reflect --project ./raw      # reflect only on nodes from this corpus

/wisdom path "DigestAuth" "OAuth"    # shortest path between two concepts
/wisdom explain "CausalSelfAttention"  # full DIKW context for a node
/wisdom god-nodes                    # highest-degree concepts across all projects

Read the full README →View source on GitHub →

Related MCP Servers

View all in Knowledge & Memory View all alternatives

Reviews

No reviews yet — be the first to share how this listing worked for you.

Frequently Asked Questions about Wisdomgraph

Add the following block to your claude_desktop_config.json under mcpServers: "mcpServers": { "wisdomgraph": { "command": "npx", "args": ["-y", "wisdomgraph"] } }

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:

Live Dynamic SVG Preview

Markdown (GitHub README)

[![AllMCPs](https://allmcps.com/api/badge/wisdomgraph?style=directory)](https://allmcps.com/mcp/wisdomgraph)

HTML Embed

<a href="https://allmcps.com/mcp/wisdomgraph"><img src="https://allmcps.com/api/badge/wisdomgraph?style=directory" alt="Wisdomgraph on AllMCPs" /></a>

Technical Specs & Signals

CategoryKnowledge & Memory

27Quality signal: Emerging · 27/100How this signal is calculated ▾

Server availabilityNot measured

Not scored for repo-hosted servers — we can't reach the running server, only its GitHub page. Hosted MCP endpoints are health-checked live.

Verified ownership8/20

Documentation & tools11/30

Adoption & activity1/15

Community engagement0/10

★ Featured

AllMCPs Server

Explore Server →

Own this project?

Free dofollow backlink: add your website and place the AllMCPs badge on it — no claim needed. We detect it automatically and keep it verified as long as the badge stays live.

Claim & get free dofollow

Share & Embed

Add our SVG badge (dark/light directory styles) or embeddable widget to your site.

Explore more

More in 🧠 Knowledge & Memory →Best MCP servers for Memory & Knowledge →Alternatives to Wisdomgraph →Install in Claude Desktop Install in Cursor Install in VS Code