DEV Community

kyoungsookim
kyoungsookim

Posted on

I Built a Self-Evolving AI Coding System

TL;DR

I built Vibe-Claude, a multi-agent system for Claude Code that:

  • Delegates tasks to specialized agents automatically
  • Creates new agents when it lacks capabilities
  • Learns from failures
  • Keeps retrying until done

GitHub: https://github.com/kks0488/vibe-claude


The Problem

Traditional AI coding: prompt → result → fix → prompt → result → fix...

You're still doing the work.


The Solution

/vibe build a login page with OAuth
Enter fullscreen mode Exit fullscreen mode

Walk away. Come back to working code.


How It Works

Multi-Agent Architecture

11 specialized agents:

Agent Model Purpose
v-analyst Opus Debugging
v-planner Opus Architecture
v-worker Sonnet Implementation
v-designer Sonnet UI/UX
v-finder Haiku Fast search

Self-Evolution

When Claude struggles with a task type:

  1. Creates a new specialized agent
  2. Saves to ~/.claude/agents/
  3. Routes future tasks to it

The system improves itself.

Failure Learning

Logs mistakes to ~/.claude/lessons-learned.md. Same mistake never happens twice.

Infinite Retry

Attempt 1: Try
Attempt 2: Different approach  
Attempt 3: Escalate model
...until success
Enter fullscreen mode Exit fullscreen mode

Quick Start

curl -fsSL https://raw.githubusercontent.com/kks0488/vibe-claude/main/scripts/install.sh | bash
Enter fullscreen mode Exit fullscreen mode

GitHub: https://github.com/kks0488/vibe-claude

Feedback welcome.

Top comments (0)