MyLoop
Runnable loop engineering for Claude Code — scheduled, stateful AI agent loops with an earned autonomy ladder.
Scheduled, stateful agent loops with an earned L1→L3 autonomy ladder, maker/checker verification, a pre-run cost gate, and pluggable engines (Claude, local Ollama, OpenCode, or any CLI). Built to run autonomous work safely without unbounded spend.
Catalog entry only — a full write-up lands closer to release.
Related across catalogs
- MyPodAI project· Demo ready
Runs multiple Claude Code autonomous tasks in parallel, each in its own isolated git worktree.
- DroidForgeClaude Code plugin· Live
Automate every repetitive Android dev task — keystore creation, signing config, version bumping, Gradle version catalog management, new app scaffolding, and release checklists.
- BonsaiAI project· Demo ready
Bonsai mode for AI agents — forces the smallest solution that works. YAGNI, enforced.
- EscalateIQAI project· Demo ready
Turn any support thread into a structured escalation report — severity, root cause, timeline, action items, and a ready-to-send customer reply.
- ImpactBoardAIAI project· Demo ready
Calculate the ROI of digital signage in real time — monthly savings, payback period, 3-year return, and an AI-generated sales summary tailored to your industry.
Want a heads-up when MyLoop releases?