Codex
OpenAI Codex agents as an alternative operator backend for hillclimb searches.
Codex is a planned alternative operator backend for
hillclimb searches: the same search loop
(draft, debug, improve, ensemble), with candidates authored by
headless OpenAI Codex agent calls (codex exec) instead of Claude Code.
Status: planned. The hillclimb backend interface is pluggable and the Codex CLI is architecturally a twin of the Claude Code CLI, but the Codex backend is not implemented yet. This page documents the intended integration surface.
What It Will Provide
| Capability | Behavior |
|---|---|
| Search operators | Candidates authored by headless codex exec calls in sandboxed workspaces. |
| ChatGPT-plan billing | Authenticate with a ChatGPT subscription via codex login. |
| API-key billing | Alternatively, an OPENAI_API_KEY bills the OpenAI API directly. |
| Credential hygiene | Same boundary as Claude Code: agent-authored code runs with credentials scrubbed; only the agent process sees the OpenAI credential. |
| Backend selection | rebase hillclimb start --backend codex once available. |
Why Multiple Agent Backends
Different coding agents draft meaningfully different solutions to the same problem — exactly the diversity the search's draft stage wants. A longer-term extension is per-operator backend mixing (for example, Codex drafts with Claude Code debugging), so one search can combine agents' strengths.
Using Codex Today
Outside hillclimb, nothing stops a Rebase function or workflow from invoking the Codex CLI as part of its own logic — the integration described here is specifically about Codex as a first-class search operator backend.