Running Claude Opus 4.7 and Codex 5.5 together in one self-directed agent system
wavefnx · x · 2026-10-16
- Developer wavefnx shows a system he built where Claude Opus 4.7 and Codex 5.5 CLIs work on their own, plan together, argue when needed to stay on goal, and play a sound when done.
- Key practice: order the agents to plan jointly and correct each other; works with any number of CLIs, though he warns against messaging CLIs you don't trust.
- His point isn't the custom harness (he has one via API) but that this collaboration can work out of the box with any official harness, with any change, at any time.
Related event: Developer Builds SMS Messaging System for Opus-Codex Agent Collaboration(4 posts)→
More from coding & agent
- vLLM ships Day-0 RL support for Beam in SkyRL, +62% LoRA decode throughput — vllm_project · 2026-10-16
- A 59-agent 'tui-review-and-fix' workflow completed in 1h18m, screenshot shows — max__drake · 2026-10-16
- Turning a Codex deep-dive article into a playable visual novel with every line sourced from transcripts — danshipper · 2026-10-16
- AI coding needs a new UI: separate chain of thought from current state and asks — robleclerc · 2026-10-16
- 'Best-of-n with resets' remains a hard-to-beat baseline for multi-agent workflows — mariofilhoml · 2026-10-16
- Troll tries to bait AI sales agent, gets a serious 3-page report — and a lesson in gating tool calls — Icy_Comfort_6220 · 2026-10-16