hannah

v0.10.6

F1 strategy engineer for your LLM garage: analyses a repository and hardware to recommend local models.

Codex1 Skill

By Lux SolariLicense: MIT0 GitHub starsUpdated last week

Directory evidence

Runtimes: Codex
Parsed components: 1 skill or MCP entry
Source updated: Sep 11, 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 hannah for Codex

Installs for the current user

codex plugin marketplace add luxsolari/lux-solari-codex-plugins
codex plugin marketplace upgrade lux-solari-codex
codex plugin add hannah@lux-solari-codex

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

Compatibility: the page URL and API slug “hannah” remain stable.

Codex: hannah@agent-plugin-marketplace → hannah@lux-solari-codex

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/luxsolari/lux-solari-codex-plugins

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

Plugin files

plugins/hannah/

├── .codex-plugin/plugin.json
└── skills/hannah/SKILL.md

Included Skills1

hannahskills/hannah/SKILL.md

Recommend the best local LLM models for a given codebase and machine. Use when the user asks which local model to run, what fits their VRAM/RAM, which Ollama or MLX model suits their repo, or wants a hardware-aware model recommendation for a project. Analyzes repo complexity + hardware, returns ranked picks.

Plugin manifests1

plugins/hannah/.codex-plugin/plugin.json

{
  "name": "hannah",
  "version": "0.10.6",
  "description": "F1 strategy engineer for your LLM garage: analyses a repository and hardware to recommend local models.",
  "author": {
    "name": "Lux Solari",
    "email": "[email protected]"
  },
  "homepage": "https://github.com/luxsolari/hannah",
  "repository": "https://github.com/luxsolari/hannah",
  "license": "MIT",
  "keywords": [
    "llm",
    "ollama",
    "models",
    "hardware",
    "repo-analysis",
    "mlx",
    "local-inference"
  ],
  "skills": "./skills/",
  "interface": {
    "displayName": "Hannah",
    "shortDescription": "Recommend local LLMs from repository and hardware analysis.",
    "longDescription": "A self-contained Python engine for local model strategy, ranking, benchmarks, and Ollama discovery.",
    "developerName": "Lux Solari",
    "category": "Productivity",
    "capabilities": [
      "repository analysis",
      "hardware detection",
      "model recommendations",
      "Ollama strategy"
    ],
    "defaultPrompt": "Analyse this repository with Hannah and recommend local LLM models."
  }
}