LoopTroop

Big coding tickets fall apart inside one endless AI chat, so LoopTroop splits each into stages with fresh, minimal context and ends in a pull request. A council of two to ten models drafts, scores, and votes on each plan, beginning with interview questions that reach you in adaptive batches. The winner refines its draft into a PRD of epics and user stories. That PRD is cut into beads, small tasks with acceptance criteria, target files, and validation steps. Each bead runs in OpenCode inside an isolated Git worktree, so your checked-out branch stays clean. During a bead the agent sees only that task, its target file, and the test file. When a bead fails, the Ralph Loop keeps a compact error trace, resets the worktree, and retries in a fresh session, so tickets can run unattended overnight. You approve specs, blueprints, and the final changes at human gates. Optional Manual QA hands you a checklist for the running app and turns failures into fix beads. A dashboard shows council progress, generated artifacts, live logs, and bead changes. Free-tier models from OpenRouter, NVIDIA NIM, or OpenCode let you start without paid API keys. LoopTroop collects no telemetry, and the project recommends a disposable VM because the agent runs with your permissions. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

LoopTroop
LoopTroop
LoopTroop
LoopTroop
LoopTroop
LoopTroop
LoopTroop

Benefits

  • Plans are debated before code exists
  • Up to ten models interview you, draft a PRD, and vote anonymously on the best plan, so ambiguities surface and get resolved before OpenCode touches your repository.
  • Failed tasks retry with clean context
  • When a bead fails, the Ralph Loop saves a compact error trace, safely resets the worktree, and restarts in a fresh session instead of patching a polluted chat.
  • Nothing merges without your sign-off
  • Specs, blueprints, and final changes each wait at a human approval gate, and every bead runs in an isolated Git worktree, so your active branch stays clean until you sign off.
  • Overnight runs without occupying your laptop
  • Tickets are built to run unattended for hours, so hosting the daemon on an always-on VPS lets OpenCode keep working through beads while your own machine stays free.

Features

  • LLM Council Planning
  • Two to ten models draft interview questions, specs, and bead blueprints, score each other with a weighted rubric, vote, then refine the winner and verify coverage.
  • Beads and Ralph Loops
  • Plans become beads with acceptance criteria, dependencies, and target files; each bead is coded, tested, and retried with fresh context and failure notes until checks pass.
  • Isolated Git Worktrees
  • OpenCode works inside dedicated Git worktrees instead of your active checkout, which keeps diffs inspectable and your main branch clean; worktrees isolate code, not command execution.
  • Live Ticket Dashboard
  • Follow council activity, generated artifacts, live execution logs, and per-bead changes in the browser, with attached projects and ticket counts on the dashboard.
  • Manual QA and Pull Requests
  • An optional checklist lets you test the running app; failed checks become QA-fix beads, improvements become new tickets, and approved work ends as a GitHub pull request.
  • Loopback-First CLI and Docker
  • Install by script, npm, Homebrew, or Docker, then run looptroop open for the UI on port 3000; the daemon binds loopback and needs an opt-in plus token to widen.

Apps Similar to LoopTroop