Multi-Agent System: AI Project Improver 🚀

Overview

AI Project Improver is a multi-agent system built using LangGraph that analyzes GitHub project descriptions and generates improved titles, summaries, tags, and feedback. The goal of this system is to simulate a real-world AI pipeline where different agents collaborate to produce structured and meaningful outputs.

Architecture

The system consists of four main agents:

• Analyzer Agent: Understands the project description
• Generator Agent: Creates a refined title and summary
• Tag Agent: Generates relevant tags using keyword extraction and LLM refinement
• Critic Agent: Reviews the output and provides improvement feedback

These agents are orchestrated using LangGraph, enabling parallel execution and structured state management.

Tools Integration

To improve reliability, the system integrates tools:

• Text Cleaner → preprocesses noisy input
• Keyword Extractor → improves tag generation

This combination of tools and LLM reduces hallucination and improves output quality.

Key Features

• Multi-agent architecture
• Tool + LLM integration
• Structured outputs
• Parallel processing with LangGraph
• Feedback loop using critic agent

Sample input 1

GitHub MCP Server

The GitHub MCP Server connects AI tools directly to GitHub's platform. This gives AI agents, assistants, and chatbots the ability to read repositories and code files, manage issues and PRs, analyze code, and automate workflows. All through natural language interactions.

Use Cases

Repository Management: Browse and query code, search files, analyze commits, and understand project structure across any repository you have access to.
Issue & PR Automation: Create, update, and manage issues and pull requests. Let AI help triage bugs, review code changes, and maintain project boards.
CI/CD & Workflow Intelligence: Monitor GitHub Actions workflow runs, analyze build failures, manage releases, and get insights into your development pipeline.
Code Analysis: Examine security findings, review Dependabot alerts, understand code patterns, and get comprehensive insights into your codebase.
Team Collaboration: Access discussions, manage notifications, analyze team activity, and streamline processes for your team.
Built for developers who want to connect their AI tools to GitHub context and capabilities, from simple natural language queries to complex multi-step agent workflows.

Sample Output 1

=== FINAL OUTPUT ===

Title: GitHub MCP Server: AI-Powered GitHub Interaction Bridge

Summary: The GitHub MCP Server acts as a bridge connecting AI tools (agents, assistants, chatbots) to the GitHub platform, enabling natural language interaction with repositories, issues, pull requests, CI/CD, and code analysis features. It allows AI to manage GitHub resources, automate workflows, analyze code, and enhance team collaboration through plain language commands. The specific technologies used to build the server are not mentioned, but it integrates with GitHub's platform and facilitates natural language interactions for AI clients.

Tags: ['Open Source Projects', 'Server Administration', 'GitHub Collaboration', 'DevOps Tools', 'Python DevOps']

Feedback: Here's short feedback to improve quality:

1. Clarify "MCP": The acronym "MCP" in the title and summary is undefined. Either spell it out (e.g., "Master Control Program," "Microsoft Certified Professional" - though unlikely here, it highlights the ambiguity) or remove it if it's not a critical, widely recognized identifier for the project.
2. Integrate Tech Stack: The summary explicitly states "The specific technologies used to build the server are not mentioned." This is a missed opportunity. Briefly mentioning the core language (e.g., Python, Node.js) or key frameworks (e.g., FastAPI, Flask, Express) would significantly enhance understanding and appeal, especially since "Python DevOps" is a tag.
3. Refine Summary's Last Sentence: Remove the self-referential sentence "The specific technologies used to build the server are not mentioned..." as it points out a gap rather than describing the project. Instead, fill that gap with actual tech details.
4. Enhance Tags:
   • Add more specific AI/NLP tags (e.g., AI Agents, Natural Language Processing, LLM Integration).
   • Consider if Server Administration is the most precise tag; API Server or Backend Service might be more accurate depending on its primary function.

Sample Input 2

🤖 Awesome GitHub Copilot

Powered by Awesome Copilot GitHub contributors from allcontributors.org
A community-created collection of custom agents, instructions, skills, hooks, workflows, and plugins to supercharge your GitHub Copilot experience.

Tip

Explore the full collection on the website → awesome-copilot.github.com
The website offers full-text search and filtering across hundreds of resources, plus the Tools section for MCP servers and developer tooling, and the Learning Hub for guides and tutorials.
Using this collection in an AI agent? A machine-readable llms.txt is available with structured listings of all agents, instructions, and skills.

📖 Learning Hub

New to GitHub Copilot customization? The Learning Hub on the website offers curated articles, walkthroughs, and reference material — covering everything from core concepts like agents, skills, and instructions to hands-on guides for hooks, agentic workflows, MCP servers, and the Copilot coding agent.

Sample Output 2

=== FINAL OUTPUT ===

Title: Awesome GitHub Copilot Project Analysis

Summary: The "Awesome GitHub Copilot" project is a community-driven, open-source collection of resources designed to enhance GitHub Copilot. It offers a wide array of custom agents, instructions, skills, hooks, workflows, and plugins, accessible via a dedicated website with search and filtering. The project also provides a learning hub with articles and guides, and its resources are available in a machine-readable llms.txt format for AI agent integration. It leverages GitHub Copilot, various AI components, and supports MCP servers and general developer tooling.

Tags: ['Python Mini-Projects', 'Open Source Projects', 'Beginner Skill Building', 'Web Development Tutorials', 'Learning Resources']

Feedback: Here's short feedback to improve quality:

1. Title: The title "Awesome GitHub Copilot Project Analysis" sounds like an analysis of the project, not the project's own title. Consider simply "Awesome GitHub Copilot" or "Awesome GitHub Copilot Project" if this is meant to be the project's public-facing name.
2. Summary: Clarify or expand on "MCP servers" in the summary, as the acronym might not be universally understood.
3. Tags: The tags are a bit generic. Make them more specific to the project's core focus (e.g., 'GitHub Copilot Resources', 'AI Agent Development', 'Copilot Customization', 'Developer Tools'). 'Python Mini-Projects', 'Beginner Skill Building', and 'Web Development Tutorials' aren't explicitly supported by the summary and might be misleading.

Conclusion

This project demonstrates how modern AI systems are built using multiple agents, tools, and orchestration frameworks. Instead of relying on a single LLM, the system distributes tasks across specialized agents, making it more scalable, modular, and closer to real-world AI applications.