MarbloBlog
Practical notes on AI agents, MCP, and multi-agent orchestration
- Product
What Is Marblo — the AI Agent Army Workspace
Marblo is a desktop app that orchestrates multiple AI coding agents simultaneously on a kanban board. Here's the concept and structure at a glance.
- Agents
7 Principles for Using AI Coding Agents Well
To use AI agents like teammates rather than tools, what do you need? Seven principles that hold up in practice, from task definition to verification.
- Orchestration
Managing Heterogeneous Agents — Placing Claude, Codex, and Antigravity by Strength
When you run different AI models together on one project, who gets what? The management principles of heterogeneous orchestration.
- Orchestration
Multi-Agent Orchestration — A Practical Structure, Seen Through Marblo
Running an army of agents, not just one. How Marblo coordinates heterogeneous AI agents simultaneously on a kanban board.
- Orchestration
Parallel Work Without Conflicts: Worktree Isolation for Agents
When several agents touch the same repo at once, they step on each other's changes. How git worktree isolation makes parallel work safe.
- Orchestration
Commanding an AI Agent Army with Tickets and Kanban
As agents multiply, 'who did what, how far' gets blurry. How to command and track an army with tickets and a kanban board.
- MCP
MCP in Depth — Safely Connecting Agents to Files, Databases, and APIs
Once you know MCP basics, the next step is safe connection. How to expose tools safely with scoped permissions, separated servers, and local execution.
- Agents
Claude Code Subagents in Practice — Working in Parallel
When and how to use Claude Code subagents, from a practical angle: splitting exploration, implementation, and review across parallel agents.
- MCP
Getting Started with MCP — the Open Standard for Connecting AI Agents to Tools and Data
What the Model Context Protocol (MCP) is, why it matters, and how Marblo uses it — in a five-minute read.