Loop Engineering is the practice of designing recurring systems for AI agents and coding agents. Instead of prompting an agent turn by turn, you build a loop that discovers work, delegates it to one or more agents, verifies the result against tests or other deterministic gates, persists state outside the model, decides what happens next, and runs again on a cadence, an event, or until a verifiable goal is reached. It sits above prompt, context, and harness engineering: those improve a single run, while loop engineering governs repeated agent work over time, including budgets, retries, escalation to humans, and stopping conditions.
Surge-style whole-home gateway and control plane for macOS — mihomo TUN, dnsmasq-powered DHCP/DNS, per-device routing, and an agent-friendly validation workspace.
Codex Orchestrator for Codex App: Loop Engineering with worktree sessions, heartbeat monitoring, persistent ledger, review routines, and evidence-label gates.
Spec-driven AI coding automation CLI. AI Loops runner for Claude Code, OpenCode, Cursor, and other agent CLIs.
Self-hosted, cloud-based agent harness.
Maestro is an open-source, multi-agent AI development framework written in Go. It orchestrates specialized AI coding agents across a deterministic software engineering workflow
Give it a PLAN.md, a mockup, or an idea. Delivery Foundry loops itself — build, verify, deploy, improve — until it's shipped.
Circuit breaker daemon for AI agent loops
htop for AI coding agents — live terminal dashboard with real-time cost tracking, context health, and spin detection