Agent Orchestration

A Model Context Protocol (MCP) server that enables multiple AI agents to share memory, coordinate tasks, and collaborate effectively across IDEs and CLI tools.

The Problem

When running multiple AI agents, they face critical coordination challenges:

1. No Turn Awareness - Agents don't know if it's their turn to act, leading to race conditions
2. File-Based Prediction - Agents predict state from files, not shared memory, causing stale reads
3. Context Drift - Parallel agents develop inconsistent understanding of the codebase
4. No Agent Discovery - Agents are unaware of other agents working on the same project
5. Duplicate Work - Multiple agents may attempt the same task simultaneously
6. Conflicting Edits - Without coordination, agents overwrite each other's changes

Solution

This MCP server provides:

• Shared Memory - Agents can store and retrieve context, decisions, and findings
• Task Queue - Turn-based task execution with dependencies
• Agent Discovery - Agents can see who else is working on the project
• Resource Locking - Prevent concurrent access to files or resources
• Coordination Status - Real-time visibility into the orchestration state
• Auto Context Sync - Automatically updates activeContext.md for easy reference

Compatibility

Works with any AI coding agent that supports MCP or AGENTS.md:

• OpenAI Codex
• Google Jules
• Cursor
• Aider
• Windsurf
• VS Code Copilot
• GitHub Copilot Coding Agent
• Devin
• And many more!

Quick Start

No installation required! Just use npx:

For Any IDE/CLI (AGENTS.md)

# Navigate to your project
cd /path/to/your/project

# Initialize with AGENTS.md
npx agent-orchestration init

This creates AGENTS.md with full orchestration instructions that work with any AI coding agent.

For Cursor IDE

# Navigate to your project
cd /path/to/your/project

# Initialize for Cursor (copies .cursor/rules/)
npx agent-orchestration init-cursor

This copies .cursor/rules/ with Cursor-specific rules.

CLI Commands

npx agent-orchestration init           # Create AGENTS.md (works with any AI agent)
npx agent-orchestration init-cursor    # Setup for Cursor IDE (.cursor/rules/)
npx agent-orchestration serve          # Run the MCP server
npx agent-orchestration help           # Show help

MCP Server Setup

Add to your MCP configuration (e.g., ~/.cursor/mcp.json for Cursor):

{
  "mcpServers": {
    "agent-orchestration": {
      "command": "npx",
      "args": ["-y", "agent-orchestration", "serve"],
      "env": {
        "MCP_ORCH_SYNC_CONTEXT": "true"
      }
    }
  }
}

The server automatically uses the current working directory as the project root.

Start Your Session

Use the bootstrap tool to start:

bootstrap

This registers you, shows current focus, pending tasks, and recent decisions.

Available Tools

Session Management

Agent Management

Shared Memory

Task Management

Coordination

Recommended Workflow

Main Orchestrator Agent

1. bootstrap                          # Start session
2. memory_set current_focus "..."     # Set project focus
3. task_create "Feature X"            # Create tasks
4. task_create "Feature Y"
5. coordination_status                # Monitor progress

Sub-Agents (Spawned for Specific Work)

1. claim_todo "Feature X"             # Register + claim in one call
2. lock_acquire "src/feature.ts"      # Lock files before editing
3. [do the work]
4. task_complete <task_id> "Done"     # Complete the task
5. agent_unregister                   # Clean up

Memory Namespaces

Use these namespaces for organization:

Configuration

Environment Variables

Architecture

┌─────────────────────────────────────────────────────────────┐
│                     IDE / CLI Tool                           │
├─────────────┬─────────────┬─────────────┬─────────────┬─────┤
│ Main Agent  │ Sub-Agent 1 │ Sub-Agent 2 │ Sub-Agent 3 │ ... │
└──────┬──────┴──────┬──────┴──────┬──────┴──────┬──────┴─────┘
       │             │             │             │
       └─────────────┴──────┬──────┴─────────────┘
                            │
                    ┌───────▼───────┐
                    │  MCP Server   │
                    │  (TypeScript) │
                    └───────┬───────┘
                            │
              ┌─────────────┼─────────────┐
              │             │             │
      ┌───────▼───┐ ┌───────▼───┐ ┌───────▼───┐
      │  Agents   │ │   Tasks   │ │  Memory   │
      │  Registry │ │   Queue   │ │   Store   │
      └───────────┘ └───────────┘ └───────────┘
              │             │             │
              └─────────────┼─────────────┘
                            │
                    ┌───────▼───────┐
                    │    SQLite     │
                    │  (per-project)│
                    └───────────────┘

AGENTS.md

This project follows the AGENTS.md format - a simple, open format for guiding AI coding agents used by over 60k open-source projects.

When you run npx agent-orchestration init, it creates an AGENTS.md file that works with:

• OpenAI Codex
• Google Jules
• Cursor
• Aider
• Windsurf
• VS Code Copilot
• And many more!

Troubleshooting

Server won't start

1. Make sure Node.js 18+ is installed: node --version
2. Check the path in your MCP config is correct

Database errors

The SQLite database is created automatically in .agent-orchestration/. If corrupted:

rm -rf .agent-orchestration/

It will be recreated on next server start.

Agents not seeing each other

• Ensure all agents are using the same cwd in the MCP config
• Check agent_list to see registered agents
• Stale agents are auto-cleaned after 5 minutes of no heartbeat

Development

For contributors and local development:

Prerequisites

• Node.js 18 or higher
• npm

Setup

# Clone the repository
git clone https://github.com/madebyaris/agent-orchestration.git
cd agent-orchestration

# Install dependencies
npm install

# Build the project
npm run build

# Watch mode (rebuild on changes)
npm run dev

# Clean build
npm run clean && npm run build

Roadmap

We're actively developing new features. Here's what's coming:

• External Memory Integration - Integration with external memory providers like Mem0, Byteover, and our own memory solution
• Enhanced Sub-Agent Knowledge - Fix limitations in knowledge sharing between main agent and sub-agents
• Research-First Workflow - When building from scratch, agents should research first and prepare all requirements before coding
• Graceful Error Handling - Better error handling and recovery across all operations
• Auto Documentation - Automatically generate documentation from and for each sub-agent + main agent interactions

Have a feature request? Open an issue!

Author

Aris Setiawan - madebyaris.com

• GitHub: @madebyaris
• Repository: agent-orchestration

License

MIT