Claude Code multi-agent

LLM Autonomous Agent Plugin For Claude

Autonomous self-learning agent plugin for Claude Code — 36 specialized subagents in a 4-tier architecture (analysis, planning, execution, validation), 27 skills, 41 slash commands across 10 categories. Pattern learning, real-time dashboard, full-stack validation, OWASP security. 100% local processing, privacy-first, cross-platform.

28 stars 16 forksMulti-agent & worktrees Plugin marketplace Source

Install

Add the plugin marketplace
/plugin marketplace add bejranonda/LLM-Autonomous-Agent-Plugin-for-Claude

Run inside Claude Code, then /plugin to pick what to install from it.

Inside Claude Code
/plugin install https://github.com/bejranonda/LLM-Autonomous-Agent-Plugin-for-Claude

Found in the project README. Check it for setup steps after installing.

From source
git clone https://github.com/bejranonda/LLM-Autonomous-Agent-Plugin-for-Claude.git

From the README

🚀 Autonomous Agent for Claude Code v8.4.5
*What if your AI agent got smarter and faster with every task?*

🚀 Installation • 🎯 Quick Start • 📚 Commands • 🛠️ Features • 📊 Dashboard

Automatic Learning System | Privacy-First | Production-Ready Analysis | Real-Time Monitoring | KPI Intelligence | OWASP Security | Auto Fixes

- Every Task Makes It Smarter
- No configuration required.
- No manual training.
- Just automatic continuous improvement across ALL models.
- 60-70% cost reduction with comprehensive KPI tracking 🆕

The autonomous agent is now smarter and more organized than ever, with revolutionary category-based commands that learn from every task and comprehensive metrics intelligence that tracks every optimization! 🚀

*Autonomous Agent Dashboard check-in! 🤖 7 Active Agents, 5 Skills, and a 97.5/100 Quality Score.*

Complete Workflow Example:

🌟 What Makes Revolutionary?
*Experience enterprise-grade autonomous intelligence that continuously evolves with every task.*

🧠 Core Innovation: Revolutionary Four-Tier Architecture

A paradigm shift from static tools to living intelligence with 36 specialized agents across 4 collaborative groups (including the master orchestrator):

🏗️ Four-Tier Group Architecture (v8.0.0+)
- Group 1 - Strategic Analysis (Brain): 8 agents analyze and recommend with confidence scores
- Group 2 - Decision Making (Council): 2 agents evaluate and create optimal execution plans
- Group 3 - Execution (Hand): 14 agents implement with comprehensive metrics
- Group 4 - Validation (Guardian): 7 agents optimize and provide continuous feedback

🚀 Revolutionary Breakthroughs

🎯 Enterprise-Grade Autonomous Operation
- 98% Success Rate: Complete independence with zero human intervention
- Intelligent Coordination: Seamless agent collaboration…
Read the full README on GitHub

Details

Language
Python
Last updated
21 June 2026
Topics
agent-frameworkai-agentsai-developmentautomationautonomous-agentsclaude-aiclaude-codeclaude-plugincode-qualitycode-reviewcontinuous-learningdashboard

FAQ

What is LLM Autonomous Agent Plugin For Claude?

Autonomous self-learning agent plugin for Claude Code — 36 specialized subagents in a 4-tier architecture (analysis, planning, execution, validation), 27 skills, 41 slash commands across 10 categories. Pattern learning, real-time dashboard, full-stack validation, OWASP security. 100% local processing, privacy-first, cross-platform. It is a multi-agent for Claude Code, from bejranonda/LLM-Autonomous-Agent-Plugin-for-Claude on GitHub.

How do I install LLM Autonomous Agent Plugin For Claude?

Run /plugin install https://github.com/bejranonda/LLM-Autonomous-Agent-Plugin-for-Claude inside Claude Code, then follow the setup in the README.

Is LLM Autonomous Agent Plugin For Claude popular?

bejranonda/LLM-Autonomous-Agent-Plugin-for-Claude has 28 GitHub stars and 16 forks. It was last updated on 21 June 2026.

More multi-agent & worktrees

TokenCode

34

yzfly/TokenCode

为 Token 燃烧而生:token 越来越便宜,质量永远稀缺——与其省 token,不如把它当燃料烧。同一道题派最多 1000 个 agent 并行竞赛、裁判择优,用冗余换质量。Go 写的开源终端 Coding Agent,类 Claude Code,可接入任意模型,对团队友好。 | Born to burn tokens — they get cheaper, quality stays scarce. A Go terminal coding agent that races up to 1,000 agents in parallel and keeps the best. Claude Code-style, any model, team-ready.

Multi-agent & worktrees

Claude Intercom

21

MuhammadTalhaMT/claude-intercom

Two-way communication bridge between Claude Code sessions using the Channels API

Multi-agent & worktrees

Claude Code Orchestration Kit

37

SirRuggie/claude-code-orchestration-kit

One expensive model orchestrates, five pinned cheaper subagents do the work. Drop-in CLAUDE.md, agents, and commands for Claude Code.

Multi-agent & worktrees

Tidebreak

32

brightwave-inc/tidebreak

Open-source, local-first desktop for AI coding agents and document work. Run Claude Code, Codex CLI, opencode, and Grok CLI in isolated Git worktrees.

Multi-agent & worktrees

Raven Nest

33

GeronimoDiClemente/raven-nest

Multi-agent terminal for Claude Code, Codex & Gemini. Open-source desktop app — Electron + React. Built for developers running multiple AI agents in parallel.

Multi-agent & worktrees

Claudemix

36

hughminhphan/claudemix

One Claude Code session, two subscriptions: Claude orchestrator + GPT executor subagents via a credential-clean loopback splitter

Multi-agent & worktrees

Browse the most popular Claude Code mods, all multi-agent & worktrees, or the skills and MCP server directories.