Skip to content

Swarek/discovery_agents

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

11 Commits
 
 
 
 
 
 
 
 

Repository files navigation

ASI-ARCH: Autonomous System Intelligence Architecture for Claude Code

"AlphaGo Moment for Model Architecture Discovery" - Implementing evolutionary AI for autonomous project architecture generation

🚀 Overview

ASI-ARCH is an advanced framework for Claude Code that implements autonomous architecture discovery through evolutionary AI principles. Based on the groundbreaking research paper that discovered 106 novel architectures through 1,773 experiments, this framework adapts the methodology using a 3-module system (Pipeline, Database, Cognition Base) to automatically discover optimal project architectures.

Key Features

  • 🧬 Evolutionary Architecture Discovery: Continuously evolves architectures through multiple generations
  • 🤖 22 Specialized Agents: Including LLM Judge and Deduplicator for rigorous evaluation
  • 📊 Composite Fitness Function: Performance (70%) + LLM Judge Score (30%) with sigmoid amplification
  • 💡 Two-Stage Strategy: Fast exploration followed by deep verification
  • 📈 Empirical Scaling Law: Tracks how fitness improves with computational investment
  • 🔄 Deduplication System: Ensures genuine innovation by preventing redundant exploration
  • 📊 Experiment Tracking: Target of 1,773 experiments matching the original research

🏗️ Architecture

The 3-Module System (Aligned with Original Paper)

┌─────────────────┐     ┌─────────────────────────────────────────┐
│ Cognition Base  │────▶│            Pipeline Module              │
│   (Knowledge)   │     │  ┌──────────┐  ┌─────────┐  ┌────────┐ │
└─────────────────┘     │  │Researcher│──│Engineer │──│Analyst │ │
         ▲              │  └──────────┘  └─────────┘  └────────┘ │
         │              └─────────────────────────────────────────┘
         │                              │
         │              ┌───────────────▼───────────────┐
         └──────────────│      Database Module         │
                        │  (Experiments & Candidates)   │
                        └──────────────────────────────┘

Agent Ecosystem

Module Key Agents Purpose
Pipeline Researcher (hypothesis-generator, cross-pollinator), Engineer (code-architect, quality-guardian), Analyst (insight-miner, llm-judge) Autonomous discovery loop
Database deduplicator, memory-architect, experiment tracker Store architectures and prevent redundancy
Cognition Base pattern-miner, knowledge-synthesizer Curated knowledge repository
Support visualizer, orchestrator, meta-learner System coordination and improvement

🎯 Usage

Basic Usage

/asi-arch Create a real-time collaborative code editor with AI assistance

Advanced Options

# Multiple evolution cycles for complex problems
/asi-arch --evolve Design a distributed ML training platform

# Interactive evolution with user feedback
/asi-arch --guide Build a blockchain-based supply chain system

# Export successful architecture as template
/asi-arch --export-template microservices-auth Design authentication microservice

📂 Project Structure

.claude/
├── slash-commands/
│   └── asi-arch.md              # Main slash command
├── agents/
│   ├── asi-arch-*.md            # 20 specialized agents
│   └── ...
├── asi-arch-context.md          # Context management rules
└── asi-arch/                    # Runtime data
    ├── knowledge-base/          # Discovered patterns
    ├── evolution-history/       # Generation tracking
    └── active-session/          # Current execution

🔧 Installation

  1. Clone this repository:
git clone https://github.com/Swarek/discovery_agents.git
cd discovery_agents
  1. The framework is automatically available in Claude Code once the repository is opened.

🌟 Example Architectures Discovered

Distributed Transaction System

Generation 1: Two-phase commit protocol (Fitness: 72)
Generation 3: Saga pattern with compensation (Fitness: 85)
Generation 5: Event sourcing with CQRS (Fitness: 94)

Real-time Analytics System

Generation 1: Batch processing pipeline (Fitness: 68)
Generation 4: Stream processing with Lambda architecture (Fitness: 87)
Generation 7: Hybrid with ML-driven optimization (Fitness: 96)

📊 How It Works

  1. Context Extraction: Analyzes your project requirements and constraints
  2. Pattern Discovery: Mines successful architectures from the knowledge base
  3. Hypothesis Generation: Creates novel architectural candidates using evolutionary algorithms
  4. Deduplication Check: Ensures genuine novelty (>85% different from existing)
  5. Two-Stage Evaluation:
    • Exploration: Quick evaluation on simplified problems
    • Verification: Deep validation of top candidates
  6. LLM Judge: Evaluates novelty and elegance (30% of score)
  7. Evolution: Continues until convergence or experiment limit
  8. Scaling Law: Tracks log(fitness) vs log(experiments) relationship

🎯 Fitness Scoring

Each architecture is evaluated on:

Composite Fitness = σ(Performance) × 0.7 + LLM_Judge_Score × 0.3

Where:

  • σ(x) = 1 / (1 + e^(-10(x-0.5))) - Sigmoid to amplify meaningful gains
  • Performance: Objective metrics (speed, scalability, efficiency)
  • LLM Judge Score: Novelty, elegance, breakthrough potential, practical impact

🤝 Contributing

ASI-ARCH is designed to evolve and improve. Contributions are welcome!

  1. Use the framework and share your discovered architectures
  2. Report issues or suggest improvements
  3. Contribute new cross-domain patterns
  4. Share success stories and case studies

📚 Based on Research

This implementation is inspired by the paper "AlphaGo Moment for Model Architecture Discovery" which demonstrated autonomous AI research capabilities in discovering novel linear attention architectures.

🔮 Future Vision

  • Architecture Marketplace: Share and discover community patterns
  • Domain Specialization: Pre-trained models for specific industries
  • Architecture Pattern Analyzer: AI-driven pattern discovery engine
  • Performance Predictions: ML-based architecture performance forecasting

📄 License

MIT License - See LICENSE file for details

🙏 Acknowledgments

  • Original ASI-ARCH research team
  • Claude Code community
  • Contributors and early adopters

"The best architecture is not designed, it's discovered through evolution."

Ready to discover your next breakthrough architecture? Try /asi-arch today!

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors