DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to use Proteus: what you can do with it

What is Proteus? Proteus is a Python framework that lets any agent harness rewrite its own files over many fresh episodes, then measures how the harness changes.

How do I use it? pip install proteus-evolve==0.4.0; then proteus run --harness minimal --arm neutral --arm review:notes --arm review:tools --seeds 4 --episodes 8 --out runs/<target>; proteus measure --harness minimal --out runs/<target>. Full steps below.

Trended earlier

View repo on GitHub

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer

What do you want to do?

4 use cases

  • Compare evolution arms offline in one afternoon

    Run the bundled offline harness under neutral and review arms and read the shift in what it builds.

    View 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.

  • Test whether a starting preference leaves a lasting mark

    Install a removable preference, then read the harness with structural distance and the crystallization test.

    View prompt
    In the Proteus repo (proteus-evolve/Proteus), run the minimal harness with a neutral arm and a review:notes arm into runs/<target>, then run proteus measure --travel. Expected output: per-surface structural distance (added, dropped, revised) and path length for each arm. Verify that the neutral arm's path length is reported alongside the review arm's, so the two can be compared.

  • Evolve a pi coding agent inside a Docker sandbox

    Run the pi harness with a DeepSeek key so it rewrites its own source inside an isolated container.

    View prompt
    In the Proteus repo (proteus-evolve/Proteus), prepare the pi-src environment, then run the pi harness with the neutral arm for 4 episodes into runs/<target>. Expected output: episode records and a snapshot per episode, with the pi source extracted into harness/src/. Verify that each episode snapshot contains a passing candidate or a restored repair candidate.

  • Score a harness against a hidden benchmark

    Attach a verifier as a hidden evaluator and keep only the harness changes that do not regress.

    View prompt
    In the Proteus repo (proteus-evolve/Proteus), write a verifier callable that returns an EvalResult, wrap it in EvaluatorSpec with Visibility.HIDDEN, and run GoalConfig.of with selection="accept_reject" against the adapter at <harness path>. Expected output: a run folder with per-episode evaluator results and accepted or rejected snapshots. Verify that the hidden evaluator's score does not appear in any observe-phase prompt.

Quick start with Proteus

  1. Check you have what it needs: 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.
  2. Open proteus-evolve/Proteus on GitHub and read the README and license.
  3. pip install proteus-evolve==0.4.0
  4. proteus run --harness minimal --arm neutral --arm review:notes --arm review:tools --seeds 4 --episodes 8 --out runs/<target> (inferred, check the README)
  5. proteus measure --harness minimal --out runs/<target> (inferred, check the README)
  6. proteus visualize --out runs/<target> then open http://127.0.0.1:8301 in a browser (inferred, check the README)

These steps come from our top use case, Compare evolution arms offline in one afternoon, which also has a copy-paste agent prompt.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for proteus-evolve/Proteus

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Proteus alternatives · Best AI repos for Software and DevOps

About this repo

  • Who it is forResearchers and developers who study or run self-evolving agent harnesses and want to measure what changes, not just a benchmark score.
  • Why it is hot111 stars, launched 70 days ago
  • LanguagePython
  • Sourcegithub.com/proteus-evolve/Proteus · Back to Hot repos

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

Add this badge to your README

Maintain Proteus? Show readers where to find these use cases. Use cases on Deduped

Markdown 

[![Use cases on Deduped](https://dedupedai.com/badge/proteus-evolve/Proteus.svg)](https://dedupedai.com/use-cases/proteus-evolve-proteus/?utm_source=github&utm_medium=badge&utm_campaign=proteus-evolve-Proteus)

HTML 

<a href="https://dedupedai.com/use-cases/proteus-evolve-proteus/?utm_source=github&amp;utm_medium=badge&amp;utm_campaign=proteus-evolve-Proteus"><img src="https://dedupedai.com/badge/proteus-evolve/Proteus.svg" alt="Use cases on Deduped" height="20"></a>

A static image, no tracking script. About the badge

Questions about Proteus

What is Proteus?

Proteus is a Python framework that lets any agent harness rewrite its own files over many fresh episodes, then measures how the harness changes. It is an open-source project on GitHub: https://github.com/proteus-evolve/Proteus.

How do I use Proteus?

pip install proteus-evolve==0.4.0; then proteus run --harness minimal --arm neutral --arm review:notes --arm review:tools --seeds 4 --episodes 8 --out runs/<target>; proteus measure --harness minimal --out runs/<target>. The use cases on this page give the full steps and a copy-paste agent prompt for each job.

Who is Proteus for?

Researchers and developers who study or run self-evolving agent harnesses and want to measure what changes, not just a benchmark score.

What can I do with Proteus?

4 use cases so far, for example: Compare evolution arms offline in one afternoon; Test whether a starting preference leaves a lasting mark; Evolve a pi coding agent inside a Docker sandbox. Each has steps and a copy-paste agent prompt.

What do I need to run Proteus?

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.

What are alternatives to Proteus?

Other hot AI repos in Software and DevOps: Deep Infer, Harness2, Orca, Opencode, Graphify.

Is Proteus safe to run?

Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.