How I Built LoopTroop: An AI Orchestrator That Builds Apps Using AI

Description and use

LoopTroop is a local, open‑source GUI orchestrator that leverages LLM councils and git worktrees to build, extend, and fix AI applications. It began with a 120‑hour planning phase, followed by over a month of implementation and refinement. The result is a tool that lets developers rapidly and reliably construct complex AI systems using multiple models and tools.

Problem

Developers struggled with complex AI app development using existing IDEs and tools like Replit, leading to overwhelm and inefficiency.

Outcome

LoopTroop enabled efficient, AI-driven app development by combining LLM councils, context engineering, and git worktrees, reducing manual coding effort and improving feature delivery.

Workflow

• 1. Allocate 120 hours purely for planning, reviewing similar projects and iterating plans across multiple LLMs.
• 2. Identify core architecture and create an architecture.md file.
• 3. Implement the plan using multiple harnesses (GitHub CLI, Claude Code, Codex, Droid, etc.), selecting best outputs and UI ideas.
• 4. Iterate over a month+ to refine core functionality.
• 5. Add features and polish until MVP aligns with vision.
• 6. Publish repository, docs, and demo video.
• 7. Continue iterative development with LoopTroop for complex work and lighter tools for quick fixes.

Evidence

The first 120 hours were pure planning. No code at all.

Source

I used a bunch of different harnesses — hammering GitHub CLI, Claude Code, Codex, Droid, and a couple others.

Source

After the core started working, I spent the next couple of months adding features and refining until it finally felt like the thing I had originally pictured in my head.

Source