Spec-driven, agentic workflow framework for AI coding agents. Turn a request into a verifiable goal loop — plan, act, verify — with durable specs and evidence in your repo. Works with Claude Code, Codex, Gemini, OpenCode, and plain CLI.

Practical patterns, starters & CLI tools for loop engineering with AI coding agents. Design systems that prompt and orchestrate agents (inspired by Addy Osmani and Boris Cherny). Includes loop-audit, loop-init, loop-cost.

Openloomi is your open-source proactive AI Mates that remembers all work details.

Inference-native Tokenmaxxing Agent Harness for Loop Engineering

OpenCode++：面向 OpenCode 的 AI 编程可靠性增强框架，为其增加上下文管理、编辑边界、命令证据、验证门禁、影响分析与修复闭环能力。OpenCode++: a Coding Agent Reliability Harness for OpenCode, adding context, edit boundaries, command evidence, verification gates, impact analysis, and repair loops.

A configurable runtime for creating governed agentic loops to reliably enable autonomous execution of complex multi-step workflows.

论文解析 Agent 系统（Agent Harness + Loop Engineering），实现结构化抽取与闭环验证优化。

Persistent project-scoped memory for Claude Code. Auto-loads on session start, structured by schema, hot/cold layered.

LoopCraft runtime harness plugin for Hermes with evidence-first execution, verification-first workflows, and self-correcting AI agent behavior. Installs as proofrail for compatibility.

Desktop harness for loop-engineering local AI-agent workflows.

AI Software Runtime（ASR）是一套面向 AI 编程任务的自治式软件工程运行时。 其核心目标不是让 AI 更会写代码，而是让 AI 生成的软件能够稳定收敛。

Local AI workbench: plan, queue, route, validate, and hand off long-running work using your already-installed Codex and Claude Code CLIs as hidden workers.

Claude Code dynamic workflow for autonomous software engineering. Zero human intervention. Spec-driven, doc-as-ground-truth pipeline that persists across sessions. Agents understand the full project — won't fix local and break global.

Curated resources and practical patterns for Loop Engineering with AI and coding agents

Contract-based multi-agent skill framework for Claude Code & Codex — compile YAML runbooks into SKILL.md with loop, parallel, and checkpoint support.

The sharpest loop engineering out there in the flagship pack. Plus a catalogue system with additional packs of subagents, skills, and hooks. Install per repo or per user. It's npm for your coding agent. The force multiplier behind the 100x engineer. Works with Claude Code, Codex, Cursor, Copilot, Gemini, Kiro.

Open-source loop engineering for auditable business briefings: claims, evidence, gates, findings, repairs, and human review.

A git-native civilization loop — laws are Issues, votes are reactions, AI agents propose & narrate, the world ticks every 1h. Loop Engineering in action.

AI agent workspace architecture, demonstrated end-to-end in Claude Code: roles library, persistent memory, hooks, scheduled agents, self-audits, loop selection, and measurement-gated self-improvement. Interactive tour, fork-ready samples.

Make your AI 10^79× stronger with AI workflow gates, evidence-backed TaskRuns, SOPs, and known-bug rules.