keepitmello/claude-codex-meight

README preview

# claude-codex-meight

<p align="center">
  <img src="./docs/hero.jpg" alt="Claude Fable 5 + Codex" width="720">
</p>

**English** | [한국어](./docs/README.ko.md)

> **A two-way harness for Claude × Codex.** Not just dispatch-and-wait: Codex workers raise questions and flag better ideas mid-run, the Claude orchestrator consults them when it's stuck, and both sides review each other's work — a real collaboration loop, not one model bossing the other around. Built on the official `openai-codex` Python SDK. CLI: `meight`.

Most Claude↔Codex bridges are built for *a human watching a terminal* — tmux panes to attach to, dashboards to click. Meight is built for the agents themselves: a Claude orchestrator and Codex workers collaborating directly, with no human in the loop. In practice that means:

- **Both directions, same thread.** Codex isn't just an executor — a worker ends a turn with a `QUESTION:` to flag a better path or a shaky assumption (not only when it's blocked), and the orchestrator answers or adjusts the direction with it. Real back-and-forth, not fire-a-task-collect-a-result.
- **Consult, don't just delegate.** Stuck on a design? The orchestrator dispatches a read-only worker to think a problem through *with* it — the sibling of code review, applied to the thinking instead of the artifact.
- **Each model checks the other.** Codex implements → a Claude agent verifies; Claude implements → a Codex worker reviews. Cross-model review catches what same-model self-review misses.
- **Supervised, on your terms.** The `start`+`wait` split lets the orchestrator pull `status` and `steer` mid-run — how often, and whether at all, is its judgment, not a fixed cadence. Progress lives in small disk files, so watching costs ~0 context.
- **One-shot when it fits.** `meight dispatch` still gives fire-and-forget for trivial, short, low-risk tasks.

```
   Claude orchestrator   ⇄   Codex worker(s)

View full repository on GitHub →