Identity Persistence Layer for Openclaw

A structured identity graph system for AI agents that synthesizes memory files into versioned, scored identity snapshots.

quriustus
v1.0.0
Feb 25, 2026
0
1.2k
0

Install & Download

1. ClawHub CLI

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

npx clawhub@latest install identity-persistence

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 identity-persistence 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 Identity Persistence Layer?

The Identity Persistence Layer is a sophisticated framework designed to manage the cognitive continuity of AI agents. It functions by analyzing raw markdown files to extract core beliefs, personality traits, and cognitive patterns, effectively turning unstructured memory into a machine-readable identity graph. This is a vital component for developers building complex Openclaw Skills who need their agents to maintain a consistent persona over time.

By utilizing versioning and statistical scoring, this skill ensures that agents do not lose their unique identity during model upgrades or long-term interactions. It provides a technical foundation for the Molting Protocol, allowing for a quantified approach to AI personality development within the Openclaw Skills ecosystem.

Identity Persistence Layer Use Cases

  • Maintaining stable agent personality during large language model upgrades.
  • Detecting and quantifying personality drift or identity fracture in autonomous agents.
  • Versioning the evolution of an AI agent's belief systems and relationship graphs.
  • Implementing deep freeze protocols for agents before major architectural changes.

How Identity Persistence Layer Works

  1. The tool parses the agent workspace for MEMORY.md and SOUL.md files.
  2. It leverages the Gemini API to perform identity extraction, identifying core beliefs and traits.
  3. The system computes a Continuity Score (0-1) using KL divergence on beliefs and MSE on traits to measure changes.
  4. A structured current_identity.json file is generated representing the identity graph.
  5. Versioned snapshots and diffs are created to provide a historical audit trail of identity changes.

Identity Persistence Layer Setup

To integrate this into your project, ensure you have a Gemini API key and an agent workspace with memory files.

# Run the full identity extraction, scoring, and saving cycle
python3 identity_manager.py

# Perform a scoring check against the last snapshot to detect drift
python3 identity_manager.py --score-only

# Initiate a deep freeze before a model upgrade
python3 identity_manager.py --freeze

Identity Persistence Layer Data Schema & Taxonomy

File/Component Purpose
current_identity.json The primary structured identity graph of the agent.
snapshots/ A directory containing versioned history files.
diffs/ Tracks specific changes between consecutive identity snapshots.
Continuity Score A 0-1 metric: >=0.90 (Stable), 0.75-0.89 (Drift), <0.75 (Fracture).

Identity Persistence Layer Advanced Features

  • Molting Protocol support for high-fidelity model transitions.
  • Automated drift detection thresholds with fracture alerts.
  • Quantitative analysis of belief systems using statistical divergence.
  • Specialized versioning for identity-driven Openclaw Skills.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*