OpenClaw-native loop engineering CLI, templates, and skill for verifiable agent work loops.

Loop Engineering CLI — workflow primitive / loop guards / evaluators / slice orchestration

Semantic loop-engineering for agent-owned, visible, interruptible continuation in Pi

Loop engineering framework for building durable, long-running agentic loops — browser, AI, or both

Autonomous coding agent based on Loop Engineering principles — convergent feedback loop from requirements to delivery

Agent loops that run on Superserve sandboxes — a warm, isolated runtime for loop engineering.

Loop Engineering — a reversible, observable multi-agent Claude Code harness for brownfield codebases. Policy lives in exit codes and artifacts on disk, not in prompts.

The meirlabs loop-engineering skill — drive a big goal end-to-end as a multi-agent orchestrator. Fan out as many haiku/sonnet/opus subagents as the goal needs, pick the model tier per task, plan first and get the plan approved before any large fan-out, ad

Estimate token budgets and daily costs for loop engineering patterns. By cadence, readiness level (L1/L2/L3), and coding agent tool.

Loop engineering readiness auditor. Compute Loop Readiness Score (L0-L3), detect activity + harness runtime, and get actionable suggestions. npx @cobusgreyling/loop-audit . --suggest

Scaffold loop engineering patterns and starters into any project. Optional --with-foundry harness stack. Supports Grok, Claude Code, Codex, Opencode and more. npx @cobusgreyling/loop-init . --pattern daily-triage --tool opencode --with-foundry

Loop engineering for AI coding agents. One canonical loop, installed into Claude Code, Gemini CLI, Codex CLI, or Cursor.

Evidence generators, normalizers, and loop-engineering adapters

MCP server for loop-engineering — exposes patterns, skills, state, and audit tools as runtime-queryable resources for AI agents

A dual-role agent harness for traceable loop engineering, evals, weak-model supervision, and self-improving agent workflows.

Install a ready-to-run loop kit from the Loop Engineering Crash Course into any project — kits only, no course, no clone.

Manage isolated git worktrees for loop engineering attempts: create, mark, cleanup, and reconcile one worktree per fix attempt.

AI agents, skills, and Loop Engineering workflows for building, testing, auditing, and releasing mobile apps.

Governed development-flow skills for AI coding agents with independent CR, Loop Engineering delivery loops, read-only triage, and approved scheduler automation.

Telemetry-first foundation for agentic loop engineering: decision-tree routing × DAG decomposition × convergence loops, plus a self-improving return path (fukuro / 復路).