🐼 Berko Multi-Agent Extension

Build AI agent teams that collaborate on complex tasks using GitHub Copilot

🎯 What is Berko?

Berko is a VS Code extension that lets you create teams of AI agents that work together on your tasks. Instead of chatting with a single AI, you can:

• 🏗️ Create specialized agents (Frontend Dev, Backend Dev, QA, Tech Lead, etc.)
• 🤝 Watch them collaborate - agents can mention and delegate to each other
• 💬 Join the conversation - type messages anytime during agent discussions
• 📝 Persist context - each conversation remembers its history
• 📋 Define team rules - each team can have its own set of shared rules

⚡ One-Time Setup (5 minutes)

Before using Berko, you need to install and authenticate the GitHub Copilot CLI.

Prerequisites:

• GitHub Copilot subscription (active)
• Node.js 18+ (for npm)

Step 1: Install GitHub Copilot CLI

Open VS Code's integrated terminal (`Ctrl+``) and run:

npm install -g @github/copilot

⚠️ Important: Install from VS Code's terminal to ensure it works immediately. Installing from external terminals may require a VS Code restart.

Step 2: Authenticate with GitHub

In the same VS Code terminal:

copilot

Once the CLI starts, type:

/login

Follow the browser authentication flow to connect your GitHub account.

Step 3: Verify Installation

copilot --version

If you see a version number, you're ready to go! 🎉

That's it! This is a one-time setup. Once installed and authenticated, Berko works across all your VS Code workspaces.

🚀 Quick Start

Step 1: Create Your First Team

1. Open VS Code in any workspace
2. Click the Berko panda icon 🐼 in the sidebar
3. Click "+ Team" to create a new team
4. Enter a name (e.g., "Development Team")

Step 2: Add Agents to Your Team

1. Expand your team in the sidebar
2. Click "+ Add Agent"
3. Enter agent names like "Senior Developer", "Junior Developer", "QA Engineer"
4. Each agent opens for editing - customize their role and skills

Step 3: Start Chatting!

1. Click on a team to select all its agents
2. Type a message and press Send
3. Watch the agents initialize and respond
4. Use @AgentName to mention specific agents

Example: Multi-Agent Collaboration

📖 Features

🧑‍🤝‍🧑 Team-Based Organization

Create multiple teams for different projects or workflows:

• Development Team (Frontend, Backend, DevOps)
• Design Team (UX Designer, UI Designer, Researcher)
• Review Team (Code Reviewer, Security Auditor, QA)

📋 Team Rules

Each team can have its own shared rules that all agents follow. Edit team rules via the context menu (right-click on team → Edit Team Rules).

Team rules are stored in .system/TeamRules.md inside each team folder. Example:

# Team Rules

## Communication Guidelines
- Always be concise and clear
- Use code blocks for any code snippets
- Mention teammates with @Name when delegating

## Workflow Rules
- Junior developers should ask Senior for code review
- QA should test all code before marking complete
- All changes must include documentation updates

## Code Standards
- Follow TypeScript best practices
- Use meaningful variable names
- Add comments for complex logic

💬 Multi-Agent Conversations

Agents collaborate through @mentions:

• You send a message → Agent responds
• Agent mentions @Teammate → Message is routed to that teammate
• Multiple agents can work in parallel when mentioned together
• The conversation flows like a real team discussion

Example: @Senior and @Junior implement login - both agents work simultaneously!

📂 Conversation History

• Switch between multiple conversations
• Each conversation maintains separate context
• Resume previous conversations with full memory

🎨 Model Selection

Choose from multiple AI models:

• Claude Opus 4.5 (default)
• Claude Sonnet 4
• GPT-4o
• And more...

⚙️ Customizable Agents

Each agent has:

• Name & Description - Who they are
• Role & Skills - What they're good at
• System Prompt - How they behave
• Response Style - How they communicate

🛠️ Agent Configuration

Agents are defined in JSON files with this structure:

{
  "$schema": "../agent-card.schema.json",
  "name": "SeniorDev",
  "displayName": "Senior Developer",
  "description": "Experienced developer who mentors juniors",
  "role": "Lead Developer",
  "skills": ["architecture", "code-review", "mentoring"],
  "responseStyle": "professional",
  "systemPrompt": "You are a senior developer with 10+ years of experience..."
}

Agent Properties

🗂️ File Structure

your-workspace/
├── agents/                      # Agent teams folder
│   ├── YourTeam/               # Team folder
│   │   ├── .team.json          # Team configuration
│   │   ├── Agent1.agent.json   # Agent definition
│   │   ├── Agent2.agent.json   # Agent definition
│   │   └── .system/            # System files
│   │       └── TeamRules.md    # Shared team rules
│   └── AnotherTeam/
│       └── ...
├── .berko-sessions/            # Session persistence (auto-generated)
└── .berko-conversations/       # Chat history (auto-generated)

⌨️ Commands

Context Menu Actions

On Teams:

• 📝 Edit Team Rules - Open the shared rules file
• 🧹 Clear Sessions - Reset all agent memory in this team
• 🗑️ Delete Team - Remove the team and all its agents

On Agents:

• 📝 Edit Agent - Open the agent configuration file
• 🧹 Clear Session - Reset this agent's memory
• 🗑️ Delete Agent - Remove the agent

💡 Tips & Tricks

Use @mentions for Directed Tasks

@Junior please implement the login form
@Senior please review @Junior's implementation

Create Workflow Chains

@Designer create mockups for dashboard, then @Frontend implement them

Leverage Specialists

Create agents with specific expertise:

• Database Expert - SQL optimization, schema design
• Security Auditor - vulnerability scanning, best practices
• Performance Engineer - profiling, optimization

Set Up Team Rules for Consistency

Define team-wide standards in TeamRules.md:

• Code formatting preferences
• Review processes
• Communication guidelines
• Project-specific conventions

🔧 Settings

Access via VS Code Settings > Extensions > Berko:

🐛 Troubleshooting

"Copilot CLI not found"

1. Open VS Code's integrated terminal (`Ctrl+``)
2. Run: npm install -g @github/copilot
3. Verify: copilot --version

If you installed from an external terminal, restart VS Code completely.

"Authentication required" / "No authentication information found"

1. Open VS Code terminal
2. Run: copilot
3. Type: /login
4. Complete the browser authentication

Agents not responding

1. Check if CLI is working: copilot --version (in VS Code terminal)
2. Check if authenticated: copilot then /status
3. Clear agent sessions (right-click on agent → Clear Session)
4. Restart VS Code

Slow initialization

First-time agent initialization takes ~30-60 seconds as it establishes sessions. Subsequent messages are faster.

📋 Requirements Summary

🤝 Contributing

🚧 Coming Soon! This project will be open-sourced and ready for contributions. Stay tuned!

📄 License

MIT License - See LICENSE for details

Happy collaborating with your AI team! 🐼