这个案例展示了 AI 代理在软件开发中的极致应用——100 个 Codex 并行工作，从代码审查到会议跟进全自动化。做开源或 SaaS 的团队看完会重新思考自己的开发流程，值得点开学习。
Peter Steinberger 分享了 OpenClaw 项目如何大规模使用 AI 代理（Codex）来重构软件开发流程。他们持续运行约 100 个 Codex 实例在云端，自动审查每个 PR 和 issue，修复旧问题、检测安全漏洞、去重 issue 并生成报告。还有代理能复现复杂环境、录制视频、自动创建 PR、扫描垃圾评论、验证性能基准，甚至在会议中主动启动工作。这种高度自动化让团队能以极精简的人力高效运转。
Interesting.
Interesting. Peter Steinberger 🦞 @steipete People freaking out over my AI spend. What nobody sees: Part of what excites me so much about working on OpenClaw is that I'm trying to answer the question: How would we build software in the future if tokens don't matter? We constant run ~100 codex in the cloud, reviewing every PR, every issue. If a fix on main lands, @clawsweeper will eventually find that 6 month old issue and close it with an exact reference. We run codex on every commit to review for security issues (as it's far too easy to miss). We run codex to de-duplicate issues and find clusters and send reports for the most pressing issues. We have agents that can recreate complex setups, spin up ephemeral crabbox.sh machines, log into e.g. Telegram, make a video and post before/after fix on the PR. There's codex that watch new issues and - if it fits our documented vision well, automatically create a PR of it. (that then another codex reviews) We have codex running that scans comments for spam and blocks people. We have codex instances running that verify performance benchmarks and report regressions into Discord. We have agents that listen on our meetings and proactively start work, e.g. create PRs when we discuss new features while we discuss them. We build clawpatch.ai to split all our projects into functional units to review and find bugs and regresssions. We do the same split for security with Vercel's deepsec and Codex Security to find regressions and vulnerabilities. All that automation allows us to run this project extremely lean. 🔗 View Quoted Tweet 💬 13 🔄 2 ❤️ 132 👀 55371 📊 19 ⚡