开源项目推荐：loop-engineering —— 让你的 AI 编码 Agent 拥有自循环与智能编排能力的实用框架

loop-engineering 是目前很火的概念，该项目提供了实用模式、启动器和 CLI 工具，帮助开发者设计系统来提示和编排 AI 编码代理（如 Claude Code、Cursor、Grok、Codex 等）。

受 Addy Osmani 和 Boris Cherny（Claude Code 负责人）理念启发，让 Agent 从“被动响应提示”转向“主动循环”完成目标，实现可持续的自动化。

核心亮点：

1. 7 个生产级循环模式（如 Daily Triage、PR Babysitter、Issue Triage），支持 L1（仅报告）→ L2（辅助）→ L3（无人值守）渐进 rollout
2. 实用 CLI 工具：loop-init（快速启动项目）、loop-audit（评估循环就绪度）、loop-cost（估算 token 消耗）
3. 五大数据块设计：自动化/调度、工作树、技能、插件/连接器、子代理 + 内存/状态
4. 内置 checklist、failure modes、anti-patterns 和 MCP 集成
5. 支持 Claude Code、Cursor、Codex 、Grok等多平台，强调工程化与可控性

该项目深入“循环工程”，让你的 AI 编码 Agent 系统更自主、可控、可持续。特别适合使用 Claude Code、Codex 等 AI 编码代理的开发者、DevOps 工程师和想从手动提示转型为系统设计师的团队。

https://github.com/cobusgreyling/loop-engineering… #AIAgent #ClaudeCode #LoopEngineering #AI工具 #开源项目 #codex

cobusgreyling/loop-engineering

Source: https://github.com/cobusgreyling/loop-engineering

Loop Engineering

Loop engineering is replacing yourself as the person who prompts the agent. You design the system that does it instead.

For developers using Grok, Claude Code, Codex, Cursor, and other AI coding agents.

A loop is a recursive goal: you define a purpose and the AI iterates (often with sub-agents, verification, and external state) until the goal is complete or the loop decides to hand off to you.

→ Interactive showcase + pattern picker
→ Loop Engineering essay (Substack)
Canonical essay by Addy Osmani

Contents

• Quick Links
• Why This Matters
• The Five Building Blocks + Memory
• Patterns
• Getting Started (5 minutes)
• Examples by Tool
• Operating & Safety
• Caveats
• Contributing
• Sources
• License

Quick Links

Why This Matters

Peter Steinberger:

“You shouldn’t be prompting coding agents anymore. You should be designing loops that prompt your agents.”

Boris Cherny (Head of Claude Code at Anthropic):

“I don’t prompt Claude anymore. I have loops running that prompt Claude and figuring out what to do. My job is to write loops.”

The leverage point has moved from crafting individual prompts to designing the control systems that orchestrate agents over time.

The Five Building Blocks + Memory

Full detail: docs/primitives.md · Cross-tool matrix: docs/primitives-matrix.md

Visual Overview

Anatomy of a Loop (Mermaid)

flowchart LR
    A[Schedule / Automation] --> B[Triage Skill]
    B --> C[Read + Write STATE / Memory]
    C --> D[Isolated Worktree]
    D --> E[Implementer Sub-agent]
    E --> F[Verifier Sub-agent<br/>tests + gates]
    F --> G[MCP / Git / Tickets]
    G --> H{Human Gate?}
    H -->|safe / allowlisted| I[Commit / PR / Action]
    H -->|risky / ambiguous| J[Escalate to human<br/>with full context]
    I --> A
    J --> A

This reference repo now runs its own validate-patterns + audit workflows on every push/PR (see .github/workflows/). We also added LOOP.md describing the loops that will maintain it.

Patterns

Not sure which to pick? Try the interactive picker or pattern-picker.

Machine-readable index: patterns/registry.yaml (7 patterns)

Getting Started (5 minutes)

# 1. Scaffold a starter (or copy manually — see starters/)
npx @cobusgreyling/loop-init . --pattern daily-triage --tool grok

# 2. Estimate token spend for your cadence
npx @cobusgreyling/loop-cost --pattern daily-triage --level L1

# 3. Audit readiness (budget + run-log now scored)
npx @cobusgreyling/loop-audit . --suggest

# 4. See scores climb: empty → L1 → L2
bash scripts/before-after-demo.sh

# 5. Start report-only (Grok example)
/loop 1d Run loop-triage. Update STATE.md. No auto-fix in week one.

All three CLIs publish to npm from tagged releases — see docs/RELEASE.md. No clone required.

Develop from source (monorepo contributors):

cd tools/loop-init && npm ci && npm test && node dist/cli.js /path/to/project --pattern daily-triage --tool grok
cd tools/loop-audit && npm ci && npm test && node dist/cli.js /path/to/project --suggest
cd tools/loop-cost && npm ci && npm test && node dist/cli.js --pattern ci-sweeper --cadence 15m

Phased rollout: L1 report → L2 assisted fixes → L3 unattended — see loop-design-checklist.

Examples by Tool

• Grok
• Claude Code
• Codex
• GitHub Actions

Operating & Safety

• Failure Modes — incident-style catalog
• Anti-Patterns — design mistakes before production
• Multi-Loop Coordination — when loops collide
• Operating Loops — cost, logging, when to kill
• Safety — denylist, auto-merge, MCP scopes
• Security — reporting and unattended automation risks
• Concepts — intent debt, comprehension debt, harness vs loop
• MCP Cookbook — connector examples by pattern

Caveats

Loop engineering amplifies judgment — both good and bad.

• Token costs can explode with sub-agents and long-running loops.
• Verification is still on you. Unattended loops make unattended mistakes.
• Comprehension debt grows faster unless you read what the loop ships.
• Two people can run the same loop and get opposite results. The loop doesn’t know. You do.

Addy Osmani:

“Build the loop. But build it like someone who intends to stay the engineer, not just the person who presses go.”

Contributing

Share production patterns, tool mappings, and failure stories. See CONTRIBUTING.md, adopters, and GitHub Discussions.

Sources

• Cobus Greyling – Loop Engineering (Substack)
• Addy Osmani – Loop Engineering
• Attribution & further reading

License

MIT

Practical, tool-aware reference for loop engineering — patterns you can clone, checklists you can ship against, and stories that include what broke.

Essay · Showcase · Cobus Greyling