npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

claude-code-ollama

v0.1.0

Published

A Claude Code skill that routes inference to a locally running Ollama model or Ollama Cloud model.

Vulnerabilities

Powered byPowered by Snyk
  • 0High
  • 0Medium
  • 0Low

Links

Git

Maintainers

vish000vish000

Keywords

agent-skillollamalocal-modelclaude-codellmself-hosted

Readme

claude-code-ollama

Run Claude Code with any open-source model via Ollama. One script. Zero dependencies.

Quick Start

bash scripts/setup.sh glm-4.7-flash          # local
bash scripts/setup.sh deepseek-v4-pro:cloud   # cloud
bash scripts/setup.sh glm-4.7-flash --launch  # auto-open new terminal

What It Does

1. Detect OS (macOS / Linux / WSL)
2. Install Ollama if missing
3. Upgrade if below v0.14.0
4. Warn if your RAM can't handle the model
5. Pull the model if not present
6. Start Ollama server if not running
7. Print launch command (or --launch to auto-open a new terminal)

How It Works

Claude Code is an agent loop. The model is swappable. This script sets three env vars that point Claude Code at Ollama instead of Anthropic's API:

Claude Code CLI → localhost:11434 (Ollama) → Model (local or cloud)

Model Recommendations

Local (runs on your hardware)

| RAM | Model | Why | |--------|------------------------|------------------------------------| | 8GB | qwen3.5:7b | Fits tight | | 16GB | qwen2.5-coder:14b | Best coding bang per GB | | 32GB | glm-4.7-flash | 128K context + native tool calling | | 64GB+ | qwen3-coder:30b-a3b | MoE — 30B total, 3B active |

Cloud (runs on Ollama's servers, :cloud suffix)

| Model | Strength | |--------------------------|-----------------------------------| | deepseek-v4-pro:cloud | Top coding benchmarks, 1M context | | kimi-k2.5:cloud | Long-horizon agentic work | | glm-5:cloud | Best open-weight on SWE-Bench Pro |

Terminal Support (--launch)

Auto-detects and opens a new tab/window:

  • macOS: iTerm2 → WezTerm → Terminal.app
  • Linux: gnome-terminal → xterm → konsole
  • WSL: Windows Terminal → cmd.exe

Falls back to printing the command if detection fails.

Troubleshooting

Invalid discriminator value error — You're probably pointing Claude Code at an OpenAI-compatible API (like LM Studio) instead of Ollama. Ollama v0.14.0+ has native Anthropic API support. Use that.

Model runs slow — Try a quantized variant: ollama pull <model>:q4_K_M. Or switch to a :cloud model.

Out of memory — The script warns you before pulling. If you ignored it... try :cloud.

License

MIT