PyPI Package Analysis with OpenClaw

OpenClaw is a capable local AI agent, but it can’t query PyPI on its own. When you ask about a Python package’s download count or latest version, it’s working from memory. AgentPatch’s pypi-package-stats tool gives it direct access to live data from the Python Package Index — downloads, versions, classifiers, and more.

Why This Matters

Python’s packaging ecosystem is huge. For most tasks there are multiple competing libraries, and the right choice depends on factors that change over time: how actively the project is maintained, whether it supports the latest Python release, and how widely it’s actually adopted. Training data goes stale. Live data from PyPI doesn’t.

With pypi-package-stats connected through AgentPatch, your OpenClaw bot can fetch current package information whenever you ask. No separate API key, no custom code — connect AgentPatch once and the tool is available alongside everything else on the marketplace.

Setup

The AgentPatch CLI is designed for AI agents to use via shell access. Install it, and your agent can discover and invoke any tool on the marketplace.

Install (zero dependencies, Python 3.10+):

pip install agentpatch

Set your API key:

export AGENTPATCH_API_KEY=your_api_key

Example commands your agent will use:

ap search "web search"
ap run google-search --input '{"query": "test"}'

Get your API key from the AgentPatch dashboard.

Install the AgentPatch skill from ClawHub — it teaches OpenClaw when to use AgentPatch and how to use the CLI:

clawhub install agentpatch

MCP Server (Alternative)

If you prefer raw MCP tool access instead of the skill, add AgentPatch to ~/.openclaw/openclaw.json:

{
  "mcp": {
    "servers": {
      "agentpatch": {
        "transport": "streamable-http",
        "url": "https://agentpatch.ai/mcp",
        "headers": {
          "Authorization": "Bearer YOUR_API_KEY"
        }
      }
    }
  }
}

Replace YOUR_API_KEY with your actual key from the AgentPatch dashboard. Restart OpenClaw and it discovers all AgentPatch tools automatically.

Example

You’re chatting with your OpenClaw bot and trying to decide on a task queue for a Django project:

“Look up the PyPI stats for celery, dramatiq, and huey. Which is the safest choice for a new project?”

Your bot fetches data for all three:

Fetching PyPI stats for celery...
Fetching PyPI stats for dramatiq...
Fetching PyPI stats for huey...

celery:
- Monthly downloads: 12.8M
- Latest version: 5.4.0 (published 1 month ago)
- Python versions: 3.8, 3.9, 3.10, 3.11, 3.12
- License: BSD-3-Clause

dramatiq:
- Monthly downloads: 1.2M
- Latest version: 1.17.1 (published 3 months ago)
- Python versions: 3.8, 3.9, 3.10, 3.11, 3.12, 3.13
- License: LGPL-3.0

huey:
- Monthly downloads: 280K
- Latest version: 2.5.2 (published 6 months ago)
- Python versions: 3.7+
- License: MIT

Celery dominates in downloads and has the most recent release. It's the standard
choice for Django task queues with the most documentation and community support.
Dramatiq is a strong alternative with a cleaner API and Python 3.13 support already
shipped. Huey is the simplest option — great for small projects, but lower adoption
and a less frequent release cadence.

For a Django project, Celery is the safest bet. The ecosystem integration (django-celery-beat,
django-celery-results) is mature and well-documented.

Three packages compared with live data, right in your chat. Your bot gave you a clear recommendation grounded in actual numbers.

Wrapping Up

Once AgentPatch is connected, your OpenClaw bot can look up PyPI stats whenever you need them. The same connection gives access to every other tool on the marketplace — npm stats, GitHub stats, web search, and more. Check out what’s available at agentpatch.ai.

← Back to blog