Source URL: https://simonwillison.net/2025/May/29/llm-github-models-015/
Source: Simon Willison’s Weblog
Title: llm-github-models 0.15
Feedly Summary: llm-github-models 0.15
Anthony Shaw’s llm-github-models plugin just got an upgrade: it now supports LLM 0.26 tool use for a subset of the models hosted on the GitHub Models API, contributed by Caleb Brose.
The neat thing about this GitHub Models plugin is that it picks up an API key from your GITHUB_TOKEN – and if you’re running LLM within a GitHub Actions worker the API key provided by the worker should be enough to start executing prompts!
I tried it out against Cohere Command A via GitHub Models like this (transcript here):
llm install llm-github-models
llm keys set github
# Paste key here
llm -m github/cohere-command-a -T llm_time ‘What time is it?’ –td
We now have seven LLM plugins that provide tool support, covering OpenAI, Anthropic, Gemini, Mistral, Ollama, llama-server and now GitHub Models.
Tags: github-actions, llm, generative-ai, llm-tool-use, ai, github, llms, anthony-shaw
AI Summary and Description: Yes
Summary: The text discusses an upgrade to Anthony Shaw’s llm-github-models plugin that enhances its functionality by supporting tool use for LLM models hosted on the GitHub Models API. This update is significant for AI professionals, particularly those working with LLMs and CI/CD in GitHub Actions, as it simplifies the process of executing AI prompts in automated workflows.
Detailed Description: The announcement highlights a new feature in the llm-github-models plugin, which is relevant to the landscape of generative AI and LLM security. Here’s an overview of its major points:
– **Upgrade to llm-github-models Plugin**: Anthony Shaw has launched an upgrade to his plugin that now supports tool use for LLM 0.26. This enhancement allows users to interact with a broader range of models available via the GitHub Models API, significantly boosting its utility.
– **Integration with GitHub Actions**: The plugin now automatically gathers the API key from the GITHUB_TOKEN, streamlining the process for users running LLMs within GitHub Actions. This integration minimizes configuration overhead and enhances the user experience, particularly for developers focusing on automation and CI/CD pipelines.
– **Practical Use Example**:
– The author provides a straightforward command-line example demonstrating how to utilize the plugin for executing a prompt with the Cohere Command A model. This practical illustration helps users understand the application and functionality of the tool.
– **Expansion of LLM Plugins**: The text notes that there are now seven LLM plugins offering tool support for various models, including notable names like OpenAI, Anthropic, and Gemini, among others. This diversification in supported models enriches the ecosystem and allows professionals to leverage multiple LLMs according to their project needs.
– **Keywords and Tags**: The text includes several tags relevant to the context of automation and generative AI, indicating the broader topics that the update touches upon.
Overall, this development in the llm-github-models plugin is particularly relevant for AI, software development, and security professionals who are looking to integrate LLM capabilities into their workflows efficiently. It indicates a trend towards increasing integration and functionality of AI tools within established platforms like GitHub, emphasizing the importance of security in these integrations.