evoclaw

Log experiences, reflect, propose, and apply identity changes to SOUL.md.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/DoggyHU/pipipax_claw_backup --skill evoclaw-doggyhu
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: evoclaw
Source: https://github.com/DoggyHU/pipipax_claw_backup/tree/main/skills/evoclaw
Command: npx skills add https://github.com/DoggyHU/pipipax_claw_backup --skill evoclaw-doggyhu

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires python, evoclaw, json, jsonl, yaml, requests, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill provides a self-evolving identity framework for AI agents, allowing them to learn, reflect, and update their own identity based on experiences and feedback.

Core Features & Use Cases

  • Experience Logging: Automatically log experiences during conversations and from external sources.
  • Reflection: Analyze logged experiences to gain insights and propose changes to the agent's identity.
  • Proposal Pipeline: Generate and propose changes to the agent's identity, subject to governance levels.
  • Change Application: Apply approved changes to the agent's identity document, SOUL.md.
  • Use Case: Imagine an AI agent that needs to evolve its own understanding of its environment and the tasks it performs. This Skill can be used to allow the agent to learn from its experiences and update its identity accordingly.

Quick Start

Run the full EvoClaw pipeline by executing the commands listed in HEARTBEAT.md.

Frequently Asked Questions about evoclaw

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I make an AI agent self-evolving and update its own identity?

To create a self-evolving AI agent, you need a framework that handles experience logging, reflection, and proposal generation to apply approved changes to the agent's identity document. This Skill facilitates that exact pipeline.

What is an AI agent identity framework and how does it work?

An AI agent identity framework defines how an agent perceives itself and its tasks. This Skill works by logging experiences, analyzing them through reflection, generating governance proposals, and applying approved changes to update the identity.

How do I log experiences for an AI agent to enable continuous learning?

You can log experiences for AI agent continuous learning by using a framework that automatically records interactions and external data. This Skill handles experience logging to feed into its reflection and identity evolution pipeline.

Do I need Python to set up a self-evolving AI agent with experience logging?

Yes, you need Python to run this self-evolving AI agent framework. It requires the Python evoclaw library along with json, jsonl, yaml, and requests dependencies for file operations, validation, and API calls.

How are proposed changes to an AI agent's identity governed and applied?

Proposed changes to an AI agent's identity are subject to governance levels within a proposal pipeline. Once approved through governance, the changes are directly applied to the agent's identity document, SOUL.md.

What's the best way to start an AI agent reflection and proposal pipeline?

The best way to start an AI agent reflection and proposal pipeline is by running the full pipeline commands. You can execute the complete workflow by running the specific commands listed in the HEARTBEAT.md file.