Agent Plugins Marketplace
All plugins

charly-ollama

Self-contained skills for running the ollama LLM-server image. Pair with charly-jupyter to expose Ollama models to Jupyter notebooks via the jupyter MCP.

CodexClaude Code3 Skills

By opencharlyLicense: MIT0 GitHub starsUpdated 1 hour ago

Directory evidence

Runtimes
Codex and Claude Code
Parsed components
3 skill or MCP entries
Source updated
Aug 28, 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 charly-ollama@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/opencharly/marketplace

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

Plugin files

ollama/
├── .codex-plugin/plugin.json
├── .claude-plugin/plugin.json
├── skills/ollama/SKILL.md
├── skills/ollama-cli/SKILL.md
└── skills/ollama-layer/SKILL.md

Included Skills3

ollamaskills/ollama/SKILL.md

Standalone Ollama LLM inference server. This candy DECLARES no GPU dependency — a backend is composed at the box level (`ollama-cuda` / `ollama-rocm`). What that yields differs by install path: on a packaged distro the base is genuinely CPU-only, while on a tarball distro the single upstream archive already contains CUDA, so the declaration is about what this candy REQUIRES, not about what ends up in the image. Runs as a supervisord service on port 11434 with persistent model storage. MUST be invoked before building, deploying, configuring, or troubleshooting the ollama box.

ollama-cliskills/ollama-cli/SKILL.md

The compiled-in `charly ollama` management CLI for a deployed Ollama server (command:ollama plugin, candy/plugin-ollama). MUST be invoked before managing models (pull/list/ps/rm/show/create/cp/push/run/stop) on a running Ollama deployment from the host.

ollama-layerskills/ollama-layer/SKILL.md

Ollama LLM server on port 11434 with model persistence; this candy declares no CUDA dependency, and a backend is composed outside it by opting a box into `ollama-cuda` or `ollama-rocm`. On a tarball distro the upstream archive already bundles CUDA, so the declaration describes what the candy REQUIRES rather than what the image contains. Use when working with Ollama, LLM serving, or local AI model inference.

Plugin manifests2

ollama/.codex-plugin/plugin.json
{
  "name": "charly-ollama",
  "description": "Self-contained skills for running the ollama LLM-server image. Pair with charly-jupyter to expose Ollama models to Jupyter notebooks via the jupyter MCP.",
  "author": {
    "name": "opencharly"
  },
  "repository": "https://github.com/opencharly/marketplace",
  "skills": "./skills/",
  "interface": {
    "displayName": "OpenCharly Ollama",
    "shortDescription": "Self-contained skills for running the ollama LLM-server image. Pair with charly-jupyter to expose Ollama models to Jupyter notebooks via the jupyter MCP.",
    "longDescription": "Self-contained skills for running the ollama LLM-server image. Pair with charly-jupyter to expose Ollama models to Jupyter notebooks via the jupyter MCP.",
    "developerName": "opencharly",
    "category": "images",
    "capabilities": [
      "Instructions"
    ],
    "defaultPrompt": [
      "Use OpenCharly Ollama for this OpenCharly task."
    ]
  }
}
ollama/.claude-plugin/plugin.json
{
  "name": "charly-ollama",
  "description": "Self-contained skills for running the ollama LLM-server image. Pair with charly-jupyter to expose Ollama models to Jupyter notebooks via the jupyter MCP.",
  "author": {
    "name": "opencharly"
  },
  "homepage": "https://github.com/opencharly/charly",
  "repository": "https://github.com/opencharly/marketplace",
  "license": "MIT",
  "keywords": [
    "charly",
    "ollama",
    "llm"
  ]
}

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

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