Neron Personal Knowledge Graph for Openclaw

A sophisticated personal intelligence engine that transforms notes and activities into a structured knowledge graph for deep life analysis.

vladikasik
v1.0.0
Mar 18, 2026
0
746
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install neron

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install neron using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is Neron Personal Knowledge Graph?

Neron is a high-performance Personal Knowledge Management (PKM) tool built on the Model Context Protocol (MCP). It allows AI agents to interact with a person's life data—including voice notes, body states, and projects—all linked within a graph database. By leveraging Apache AGE and Voyage AI embeddings, Neron enables a level of self-reflection and data retrieval that goes beyond simple note-taking.

As part of the Openclaw Skills ecosystem, Neron provides developers and power users with a framework for building truly personalized AI assistants. It doesn't just store data; it understands relationships, tracks emotional valence, and identifies behavioral patterns over time, making it an essential component for those seeking a digital second brain.

Neron Personal Knowledge Graph Use Cases

  • Tracking mood and energy trends over weeks to identify productivity triggers.
  • Semantic search across years of notes to find conceptual connections without exact keyword matches.
  • Managing complex project tasks and people relationships within a unified graph.
  • Analyzing the impact of physical habits, such as sleep or substances, on next-day cognitive performance.

How Neron Personal Knowledge Graph Works

  1. Input data is captured as a primary note entity via voice or text interfaces.
  2. The system automatically extracts specific entities like mood, activities, and food, populating the graph via read-only extraction fields.
  3. Voyage AI generates vector embeddings for all core entities to facilitate semantic search and retrieval-augmented generation (RAG).
  4. The agent uses tools like Cypher queries or semantic search to navigate the Apache AGE graph and provide natural language insights to the user.

Neron Personal Knowledge Graph Setup

To integrate this capability into your environment, point your MCP client to the Neron endpoint. Use the following steps to verify your installation:

# Configure your MCP client to use the Neron endpoint
# Endpoint: https://mcp.neron.guru/mcp

# Call get_stats to verify the connection and see your current graph size
mcp call get_stats

Neron Personal Knowledge Graph Data Schema & Taxonomy

Neron organizes information into a strict taxonomy of core and extraction entities to maintain graph integrity.

Type Category Key Fields
note Core text, created_at
task Core title, status, priority, due_at
ai_note Core content, note_type (insight, synthesis)
mood Extraction valence, energy, emotions
activity Extraction activity_type, duration, location
edge Graph from_id, to_id, relationship_type

All entities are connected via a directed graph (Apache AGE), supporting temporal chains and relational mapping.

Neron Personal Knowledge Graph Advanced Features

  • Semantic Search: Uses Voyage AI to find conceptually related content across 11 different entity types.
  • Cypher Query Support: Run raw graph database queries for complex analytics, such as correlation between activities and mood.
  • Automated Insights: The system generates ai_note entities to record patterns and observations, building long-term agent memory.
  • Temporal Chaining: Notes are automatically linked in a temporal sequence (AFTER relationship) for chronological storytelling.
  • Deep Node Context: Retrieve the full neighborhood of a specific node using Breadth-First Search (BFS) to understand historical context.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*