{"slug": "show-hn-ai-whisper-claude-works-better-when-codex-watches-its-back", "title": "Show HN: AI-whisper – Claude works better when Codex watches its back", "summary": "Developer released ai-whisper v0.7.0, an open-source terminal tool that pairs AI coding agents like Claude and Codex in structured workflows to improve code quality through collaborative review. The tool uses a single-baton relay and evaluator-gated loops to automate spec-driven development, bug fixing, and deliberation tasks.", "body_md": "# ai-whisper\n\nterminal-first relay for paired ai coding agents, driven by structured workflows\n\nv0.7.0 — open source, on npm, actively used personally.\n\n## what it does\n\nai-whisper pairs two coding agents in your terminal — mount any two of Claude, Codex, and [ezio](/projects/ai-ezio), provider-agnostic by design. They share a single baton — one owns the turn at a time — and structured workflows drive the collaboration, with an evaluator gating each round. The relay isn’t tied to any one arrangement; today’s workflows pair an implementer and a reviewer (spec-driven-development, ralph-loop, complex-bug-fixing, deliberation).\n\n## why\n\nHard agent tasks go better with a second agent reviewing. Whisper makes that pairing feel like one workflow instead of two terminals pretending to talk to each other.\n\nai-whisper was built this way: nearly every feature started as a spec run through its own spec-driven-development workflow.\n\n## # features\n\n- structured workflows — spec-driven-development, ralph-loop, complex-bug-fixing, deliberation\n- single-baton relay — one owner at a time, not a swarm\n- role-agnostic — workflows assign the roles (today: implementer + reviewer)\n- autonomous loops gated by an llm evaluator\n- pausable, resumable runs — pause a healthy run mid-flight, recover a stuck one, don't restart\n- real mounted claude / codex / ezio sessions as the source of truth\n\n## workflows\n\nA workflow is a structured loop — phases, gates, round budgets — not a long prompt. Pick by the shape of the work:\n\n**spec-driven-development**— when you can describe “done” up front. Sharpens a spec into a plan, then executes it under review.** ralph-loop**— when you can’t. Grinds an open-ended goal chunk-by-chunk, a reviewer gating each one.** complex-bug-fixing**— when a bug is reported but the root cause isn’t. Three phases (diagnosis → fix-and-verify → post-mortem), with the implementer required to reproduce the bug — a committed failing test, not speculation from reading code.**deliberation**— when the idea is still fuzzy and you can’t describe “done” yet. An Explorer and Challenger map the space (objectives → approaches → tradeoffs → synthesis), then hand back a committed findings doc to take into brainstorming or SDD.\n\nWhichever you pick, you write the spec, goal, or bug report; the run converges on the criteria you set — so a precise artifact is most of the outcome.\n\nAutonomous covers the *loop*, not the ship decision. A finished run is a strong draft: you still read the diff, run it, and QA it before it lands. ai-whisper does the convergence and hands you the full trail to judge fast.\n\n## see it run\n\nA real `spec-driven-development`\n\nrun: Claude (left) and Codex (middle) work in their own mounted sessions while the dashboard (right) tracks the baton handoffs and per-phase verdicts.\n\n## # install\n\n```\nnpm install -g ai-whisper\n```\n\n", "url": "https://wpnews.pro/news/show-hn-ai-whisper-claude-works-better-when-codex-watches-its-back", "canonical_source": "https://ai-creed.dev/projects/ai-whisper/", "published_at": "2026-06-27 15:07:57+00:00", "updated_at": "2026-06-27 15:34:36.092045+00:00", "lang": "en", "topics": ["ai-tools", "developer-tools", "large-language-models", "ai-agents"], "entities": ["Claude", "Codex", "ai-whisper", "npm"], "alternates": {"html": "https://wpnews.pro/news/show-hn-ai-whisper-claude-works-better-when-codex-watches-its-back", "markdown": "https://wpnews.pro/news/show-hn-ai-whisper-claude-works-better-when-codex-watches-its-back.md", "text": "https://wpnews.pro/news/show-hn-ai-whisper-claude-works-better-when-codex-watches-its-back.txt", "jsonld": "https://wpnews.pro/news/show-hn-ai-whisper-claude-works-better-when-codex-watches-its-back.jsonld"}}