LoopTroop is a local, open-source GUI app for running complex, long-running AI coding tickets from start to finish - across multiple projects and tickets without leaving the app. Instead of one model that suffers context-rot, an LLM Council drafts, anonymously votes, and merges the best ideas to plan. Work is split into atomic Beads run in isolated git worktrees, and Ralph Loops refresh each failed attempt. Every step is transparent, auditable, and observable from one pane.
No reviews yetBe the first to leave a review for LoopTroop
Maker
📌
Why do AI coding agents derail on large tasks? Context-rot.
LoopTroop solves this locally and open-source. An LLM Council designs the plan, atomic Beads execute in isolated worktrees, and Ralph Loops recover when code fails.
This app is the alternative to agentic ai tools (like claude code, codex, opencode) in a cool GUI with kanban boards and uses modern AI principles - context engineering, llm councils, ralph loops, etc
Any feedback is highly appreciated, and I'm happy to answer any questions or comments below.
Report
Maker
Just hit 100 🌟 on GitHub for LoopTroop v0.4!
LoopTroop is a free & open-source local AI coding orchestrator that turns tickets into real PRs without endless chat drift.
⚙️ LLM councils plan the work
🔁 Ralph loops iterate & perfect it
🌲 OpenCode worktrees ship the PR
Built with human approval gates, planned task beads, and local control.
The first 100 stars are the hardest. Huge thanks to everyone supporting the project!
Why do AI coding agents derail on large tasks? Context-rot.
LoopTroop solves this locally and open-source. An LLM Council designs the plan, atomic Beads execute in isolated worktrees, and Ralph Loops recover when code fails.
This app is the alternative to agentic ai tools (like claude code, codex, opencode) in a cool GUI with kanban boards and uses modern AI principles - context engineering, llm councils, ralph loops, etc
Any feedback is highly appreciated, and I'm happy to answer any questions or comments below.