$ loading_
Run automated optimization loops in codebases against measurable performance targets.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "codex-autoresearch" yet — see the docs or source repo.
Run an automated optimization loop in this codebase to reduce total test suite runtime. Inspect the existing test scripts, try small reversible changes, repeatedly run the tests, and compare total time. Return the best changes, performance comparison, and risk notes.
A test runtime optimization report with the best code changes, before/after timing, and rollout recommendations.
Run an automated optimization loop for this frontend project with minimizing bundle size as the goal. Repeatedly try dependency swaps, lazy loading, and config changes based on the build script, track size changes after each build, and output the most effective combination of changes.
A bundle size optimization plan including key changes, size reduction results, and verification steps.
Run an automated optimization loop in this backend codebase with query latency as the main metric. Execute the benchmark script, try index tuning, query rewrites, caching strategies, or code path optimizations, compare each iteration, and return the highest-impact solution.
A query performance optimization report with the best changes, latency improvements, and possible trade-offs.
Collaborate with Codex in Claude Code for coding, edits, and debugging.
Configure Codex CLI settings, skills, and prompts for faster coding workflows.
Delegate large code reads, patches, and tests to a cheaper async worker.
Build local repo memory for fast code search and visual navigation.
Run Codex CLI tasks in parallel with isolated worktrees and live monitoring.
Track and analyze Codex token usage, costs, caching, and thread patterns locally.