The orchestration layer under your coding agent. Turns work into a typed graph, runs one model per node, and takes the verdict from outside the model — exit codes, write-set checks, and a cross-family verifier. MCP server, 50 tools, bring your own models.
View on GitHub →
🔍 Audit Wallet Slippage →
Quick Install
Copy the config for your editor. Some servers may need additional setup — check the README.
Claude Desktop
Claude Code
Cursor
Add to claude_desktop_config.json:
{
"mcpServers": {
"oh-my-dag": {
"command": "npx",
"args": [
"-y",
"AbyssCN/oh-my-dag"
]
}
}
}📋 Copy
Run in terminal:
claude mcp add oh-my-dag npx -y AbyssCN/oh-my-dag📋 Copy
Add to .cursor/mcp.json:
{
"mcpServers": {
"oh-my-dag": {
"command": "npx",
"args": [
"-y",
"AbyssCN/oh-my-dag"
]
}
}
}📋 Copy
README Excerpt
<p align="center"> <img src="assets/diagrams/omd-layers.svg" alt="Where omd sits: your coding agent on top, omd underneath over MCP, then memory and models" width="920"> </p> <p align="center"> <strong>The orchestration layer under your coding agent.</strong> </p> <p align="center"> <a href="docs/guide/mcp-tools.md"><img src="https://img.shields.io/badge/MCP%20tools-50-c9a227?style=flat&colorA=140f0a" alt="50 MCP tools"></a>
Topics
agent-orchestration agentic-ai ai-agent bun claude-code coding-agent dag llm llm-orchestration mcp mcp-server model-agnostic multi-agent orchestration typescript