Hi HN, I've been experimenting a lot with autonomous coding agents (like OpenClaw and various CLI tools), but I kept running into two major roadblocks when trying to use them for actual production work: Security & State: Most agents require running a persiste…
AI coding agents are powerful they can plan features, write code, and run tests. But without coordination, they become chaotic. Multiple agents working on the same codebase need someone to break down… [+11164 chars]
