{
 "schema_version": 1,
 "generated": "2026-10-26",
 "id": "proteus-evolve-proteus--compare-evolution-arms-offline",
 "repo": "proteus-evolve/Proteus",
 "repo_url": "https://github.com/proteus-evolve/Proteus",
 "repo_slug": "proteus-evolve-proteus",
 "title": "Compare evolution arms offline in one afternoon",
 "page_title": "How to compare evolution arms offline in one afternoon with Proteus",
 "summary": "Run the bundled offline harness under neutral and review arms and read the shift in what it builds.",
 "who": "A researcher or developer who wants to see how an action preference changes a self-evolving harness, without an API key or Docker.",
 "problem": "Reading a self-evolving harness by hand is slow, and it is hard to tell whether a change came from the preference or from noise.",
 "outcome": "A per-arm table of notes and tools built, a behavioural R and p value, and a local visual replay of the runs.",
 "steps": [
  "`pip install proteus-evolve==0.4.0`",
  "`proteus run --harness minimal --arm neutral --arm review:notes --arm review:tools --seeds 4 --episodes 8 --out runs/<target>` (inferred, check the README)",
  "`proteus measure --harness minimal --out runs/<target>` (inferred, check the README)",
  "`proteus visualize --out runs/<target>` then open http://127.0.0.1:8301 in a browser (inferred, check the README)"
 ],
 "agent_prompt": "In the Proteus repo (proteus-evolve/Proteus), install proteus-evolve==0.4.0 and run the minimal harness with the neutral, review:notes and review:tools arms, writing output to runs/<target>. Expected output: a per-arm table of notes and tools counts plus a behavioural R and p value from proteus measure. Verify that the measure output includes a p value and that the review arms show a different notes or tools count than neutral.",
 "agents": [
  "any"
 ],
 "difficulty": "Intermediate",
 "time": "15 minutes",
 "basis": "readme",
 "caveat": "The minimal harness uses a mock policy, so the numbers show the pipeline working offline, not how a real model behaves.",
 "category": "Software and DevOps",
 "tags": [
  "Software and DevOps"
 ],
 "lang": "python",
 "requirements": [
  "Python 3.10 or newer",
  "pip to install proteus-evolve==0.4.0 (no model SDK is required for the minimal harness)",
  "For real harnesses: Docker and a DeepSeek or Codex key, as listed in the harness table"
 ],
 "risk": "none",
 "seen_in_the_wild": false,
 "mentioned_publicly": false,
 "risks": [],
 "best": true,
 "score": 1.0,
 "evidence": [],
 "url": "https://dedupedai.com/use-cases/proteus-evolve-proteus/compare-evolution-arms-offline/",
 "md": "https://dedupedai.com/use-cases/proteus-evolve-proteus/compare-evolution-arms-offline/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/proteus-evolve-proteus--compare-evolution-arms-offline.json",
 "api_version": "v1"
}