🚀 GitHub AI Agent

---

🧪 Evaluation Badges

| Claude | Gemini | OpenAI | Llama |
|--------|--------|--------|-------|
| | | | |

---

- 🤖 GitHub Agent is an LLM-powered agent built using the LangGraph ReAct Agent workflow and MCP tools.
- 🌐 Protocol Support: Compatible with ACP and A2A protocols for integration with external user clients.
- 🛡️ Secure by Design: Enforces GitHub API token-based authentication and supports external authentication for strong access control.
- 🔌 Integrated Communication: Uses langchain-mcp-adapters to connect with the GitHub MCP server within the LangGraph ReAct Agent workflow.
- 🏭 First-Party MCP Server: The MCP server is generated by our first-party openapi-mcp-codegen utility, ensuring version/API compatibility and software supply chain integrity.

---

🏗️ Architecture

flowchart TD
  subgraph Client Layer
    A[User Client ACP/A2A]
  end
subgraph Agent Transport Layer

    B[AGNTCY ACP<br/>or<br/>Google A2A]

  end
subgraph Agent Graph Layer

    C[LangGraph ReAct Agent]

  end
subgraph Tools/MCP Layer

    D[LangGraph MCP Adapter]

    E[GitHub MCP Server]

    F[GitHub API Server]

  end
A --> B --> C

  C --> D

  D -.-> C

  D --> E --> F --> E

✨ Features

- 🤖 LangGraph + LangChain MCP Adapter for agent orchestration
- 🧠 Azure OpenAI GPT-4 as the LLM backend
- 🔗 Connects to GitHub via a dedicated GitHub MCP server
- 🔄 Multi-protocol support: Compatible with both ACP and A2A protocols for flexible integration and multi-agent orchestration
- 📊 Comprehensive GitHub API Support:
- Repository Management
- Issue Management
- Pull Request Management
- Branch Management
- Commit Operations
- Project Management
- Team Collaboration

---

🚀 Getting Started

1️⃣ Configure Environment

Setting Up Azure OpenAI

1. Go to Azure Portal
2. Create or select your Azure OpenAI resource
3. Navigate to "Keys and Endpoint" section
4. Copy the endpoint URL and one of the keys
5. In Azure OpenAI Studio:
- Create a deployment for GPT-4
- Note down the deployment name
- You'll need these values for your .env file:
- AZURE_OPENAI_API_KEY
- AZURE_OPENAI_ENDPOINT
- AZURE_OPENAI_DEPLOYMENT

Setting Up GitHub Token

1. Go to GitHub.com → Settings → Developer Settings → Personal Access Tokens → Tokens (classic)
2. Click "Generate new token (classic)"
3. Give your token a descriptive name
4. Set an expiration date (recommended: 90 days)
5. Select the required permissions:
- repo (Full control of private repositories)
- workflow (Update GitHub Action workflows)
- admin:org (Full control of orgs and teams)
- admin:public_key (Full control of public keys)
- admin:repo_hook (Full control of repository hooks)
- admin:org_hook (Full control of organization hooks)
- gist (Create gists)
- notifications (Access notifications)
- user (Update ALL user data)
- delete_repo (Delete repositories)
- write:packages (Upload packages to GitHub Package Registry)
- delete:packages (Delete packages from GitHub Package Registry)
- admin:gpg_key (Full control of GPG keys)
- admin:ssh_signing_key (Full control of SSH signing keys)
6. Click "Generate token"
7. Copy the token immediately (you won't be able to see it again)
8. Save this as your GITHUB_PERSONAL_ACCESS_TOKEN

Port Configuration

- Default ports:
- A2A Agent: 8000
- MCP Server: 9000
- If port 8000 is already in use:
1. Choose an available port (e.g., 8001, 8002, etc.)
2. You'll need to update this in both:
- Your .env file as A2A_AGENT_PORT
- Your Docker run command port mapping

Now, create a .env file in the root directory with the following configuration:

```env
############################