{
 "schema_version": 1,
 "generated": "2026-10-20",
 "id": "makezur-agenticstar--compare-codex-and-claude-runs",
 "repo": "makezur/agenticSTAR",
 "repo_url": "https://github.com/makezur/agenticSTAR",
 "repo_slug": "makezur-agenticstar",
 "title": "Compare Codex and Claude Code on the same capture",
 "page_title": "How to compare Codex and Claude Code on the same capture with Agentic STAR",
 "summary": "Run the same capture with both supported agents and compare the resulting poses.",
 "who": "A researcher evaluating which coding agent produces better articulated reconstructions on a fixed capture.",
 "problem": "Agent choice changes results, and the repo supports two agents with separate supervisors.",
 "outcome": "Two runs on one capture, each with its own mesh/pose.json and iteration renders that can be compared side by side.",
 "steps": [
  "Run `export OPENAI_API_KEY=sk-...` and then `tools/install_codex_bwrap.sh` once.",
  "Run `tools/run_kf.sh --agent codex examples/garden_shears/capture:0`. (inferred, check the README)",
  "Run `tools/agent-supervisor` to watch the Codex run.",
  "Run `tools/run_kf.sh --agent claude --timeout-hours 4 examples/garden_shears/capture:0` for the Claude run.",
  "Compare the mesh/pose.json and side-by-sides under iterations/ from each runs/ directory."
 ],
 "agent_prompt": "In the agenticSTAR repo, run tools/run_kf.sh on examples/garden_shears/capture:0 once with --agent codex and once with --agent claude. Expect two runs/ directories, each with mesh/pose.json. Verify that both runs finished or hit their timeout before comparing outputs.",
 "agents": [
  "claude-code",
  "codex"
 ],
 "difficulty": "Advanced",
 "time": "10 hours",
 "basis": "readme",
 "caveat": "The paper results used a critic branch with GPT-5.6-Sol, and the README says newer models should work without it, so a fair comparison needs the same settings on both sides.",
 "category": "Research",
 "tags": [
  "Research"
 ],
 "lang": "python",
 "requirements": [
  "Linux x86_64 host with an NVIDIA GPU",
  "micromamba, git, curl, tar, xz, python3, tmux, bubblewrap, iproute2 and ffmpeg installed on the host",
  "Root or CAP_NET_ADMIN for the sandbox network namespace",
  "An Anthropic API key for Claude Code or an OpenAI API key for Codex",
  "claude and/or codex available on PATH"
 ],
 "risk": "none",
 "seen_in_the_wild": false,
 "mentioned_publicly": false,
 "risks": [
  {
   "tag": "credentials",
   "notice": "Both API keys are needed, so keep them out of shared logs and terminal history, since the install scripts store the Claude key in a state dir outside the checkout."
  }
 ],
 "best": false,
 "score": 0.8,
 "evidence": [],
 "url": "https://dedupedai.com/use-cases/makezur-agenticstar/compare-codex-and-claude-runs/",
 "md": "https://dedupedai.com/use-cases/makezur-agenticstar/compare-codex-and-claude-runs/index.md",
 "disclaimer": "Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked \"Seen in the wild\", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email hello@dedupedai.com and we will look at it promptly.",
 "api": "https://dedupedai.com/api/v1/usecases/makezur-agenticstar--compare-codex-and-claude-runs.json",
 "api_version": "v1"
}