You describe what you want. The orchestrator breaks it into tasks and coordinates 4 Claude Code agents working in parallel. No babysitting. No context-switching. Just ship.
A master orchestrator watches your 4 agents, dispatches tasks, detects when they're stuck, and learns from every session. You describe the goal — it figures out the rest.
A 5th Claude Code instance coordinates the other four. It reads their output, detects status changes, dispatches tasks, and intervenes when things go wrong — via browser automation.
Research, build, test, and verify — all running simultaneously in a browser-based terminal grid. Each agent has its own scope, its own context, and real-time status detection.
The orchestrator measures tool effectiveness, evolves playbooks, and rates what works — based on real session data. It gets smarter every time you use it.
No configuration files. No orchestration boilerplate. Just describe what you want to build.
Configures MCP server for Claude Code integration and adds the orchestrator prompt. Run once, then restart Claude Code.
npx ninja-terminals --setup
A 5th Claude Code instance — the orchestrator — reads your goal, breaks it into parallel subtasks, and dispatches each one to a terminal via browser automation.
Four agents run in parallel while the orchestrator monitors them — detecting status changes, unblocking stuck agents, and re-dispatching work. You watch. It coordinates.
Try the basics free. Upgrade for the orchestrator that coordinates your agents and evolves with every session.