algorithm-evolve

v0.1.0

Evolve and score executable algorithms with Monte Carlo graph search.

Codex2 Skills

By MLEvolve contributorsLicense: Apache-2.00 GitHub starsUpdated 2 hours ago

Directory evidence

Runtimes: Codex
Parsed components: 2 skill or MCP entries
Source updated: Aug 27, 2026
Manifest status: Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install plugin

Installs for the current user

codex plugin marketplace add IchenDEV/agent-plugin-mkt
codex plugin marketplace upgrade agent-plugin-marketplace
codex plugin add algorithm-evolve@agent-plugin-marketplace

Paste and run these commands in a terminal with Codex. They add and refresh the PluginsMP catalog, then install this plugin.

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually

$ git clone https://github.com/Azhi-ss/algorithm-evolve

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The repository root is the plugin root.

Plugin files

algorithm-evolve/

├── .codex-plugin/plugin.json
├── skills/algorithm-evolve/SKILL.md
└── skills/algorithm-evolve-resume/SKILL.md

Included Skills2

algorithm-evolveskills/algorithm-evolve/SKILL.md

Evolve executable algorithms, optimization routines, prompts, configurations, or agent workflows with Monte Carlo graph search and independently scored subagents. Use when Codex must search several candidate approaches under explicit tests, metrics, rubrics, constraints, and a time or iteration budget while preserving a queryable evidence trail.

algorithm-evolve-resumeskills/algorithm-evolve-resume/SKILL.md

Inspect and continue an interrupted Algorithm Evolve search from its local SQLite state. Use when the user asks to resume, continue, recover, or report progress for an algorithm optimization previously started with algorithm-evolve, or explicitly invokes $algorithm-evolve-resume.

Plugin manifests1

.codex-plugin/plugin.json

{
  "name": "algorithm-evolve",
  "version": "0.1.0",
  "description": "Evolve and score executable algorithms with Monte Carlo graph search.",
  "author": {
    "name": "MLEvolve contributors"
  },
  "repository": "https://github.com/InternScience/MLEvolve",
  "license": "Apache-2.0",
  "keywords": [
    "algorithm",
    "optimization",
    "mcgs",
    "agents"
  ],
  "skills": "./skills/",
  "interface": {
    "displayName": "Algorithm Evolve",
    "shortDescription": "Search and score executable algorithm variants.",
    "longDescription": "Coordinate isolated subagents to propose, evaluate, refine, repair, and fuse algorithm candidates under an explicit budget.",
    "developerName": "MLEvolve contributors",
    "category": "Productivity",
    "capabilities": [
      "Interactive",
      "Write"
    ],
    "defaultPrompt": [
      "Optimize this algorithm against its test and benchmark suite."
    ]
  }
}

For maintainers

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[algorithm-evolve on Agent Plugins Marketplace](https://pluginsmp.com/plugins/algorithm-evolve)