self-evolving-agent

Official

Self-evolving AI agents.

Authorplurigrid
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Darwin Gödel Machine patterns enable self-improving AI agents that autonomously evolve capabilities, memory, and tools through interaction and feedback, supporting lifelong learning and open-ended optimization.

Core Features & Use Cases

  • Darwin Gödel Machine architecture: archive, sampler, mutator, evaluator, validator
  • Open-ended evolution: mutate agent code and re-evaluate fitness
  • Long-term memory: retain successful policies and exploit past discoveries
  • Co-evolution: multi-agent interaction and knowledge sharing

Quick Start

Sample an agent from the archive, mutate its code using an LLM-based mutator, evaluate fitness, and prune the archive to maintain diversity.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: self-evolving-agent
Download link: https://github.com/plurigrid/asi/archive/main.zip#self-evolving-agent

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.