Version updated for https://github.com/MattJColes/lgtmaybe to version lgtmaybe-v2.5.0. This action is used across all versions by ? repositories. Action Type This is a Composite action. Go to the GitHub Marketplace to find the latest changes. Action Summary The lgtmaybe GitHub Action is a tool designed to review pull requests or merge requests across multiple version control platforms (GitHub, GitLab, and Gitea) using AI-based models. It generates inline comments on changes, focusing on logic errors, security vulnerabilities, missing tests, outdated code, performance regressions, unnecessary complexity, intent alignment, and unnecessary code, all without executing the code. The tool is designed to be secure by not running any of the PR’s code and redacting sensitive information before submission to the model.

Version updated for https://github.com/MattJColes/lgtmaybe to version lgtmaybe-v2.3.0. This action is used across all versions by ? repositories. Action Type This is a Composite action. Go to the GitHub Marketplace to find the latest changes. Action Summary lgtmaybe is a provider-agnostic PR reviewer designed to automatically review and assess changes in pull requests. It fetches the diff from GitHub using the API and reviews each line, considering context by reading surrounding lines. The action surfaces issues such as logic errors, security vulnerabilities, missing tests, outdated code, performance regressions, complexity, intent, and unnecessary complexity. lgtmaybe uses OpenAI models to generate inline comments and a summary of the review. It is designed to be provider-agnostic and supports local Ollama as well as any OpenAI-compatible endpoint without requiring static keys for cloud providers.

Version updated for https://github.com/MattJColes/lgtmaybe to version lgtmaybe-v2.2.0. This action is used across all versions by ? repositories. Action Type This is a Composite action. Go to the GitHub Marketplace to find the latest changes. Action Summary lgtmaybe is a tool designed to automate and streamline the code review process by analyzing pull request diffs using an AI model. It helps identify logic errors, security vulnerabilities, missing tests, outdated code, performance regressions, unnecessary complexity, intent misalignment, and potential “ponytail” code (code that could be removed). The action reviews files line-by-line, considering context from surrounding lines, and categorizes findings into nine categories: security, correctness, code health, artefacts. It is provider-agnostic and supports multiple OpenAI-compatible endpoints.

Version updated for https://github.com/MattJColes/lgtmaybe to version lgtmaybe-v2.1.2. This action is used across all versions by ? repositories. Action Type This is a Composite action. Go to the GitHub Marketplace to find the latest changes. Action Summary lgtmaybe is a tool that automates code reviews by analyzing pull requests against a set of predefined criteria. It uses an AI model to detect bugs, security vulnerabilities, and other issues in the code changes, providing inline comments and a summary of the review results. The action supports various hosted providers, local Ollama models, and OpenAI-compatible endpoints.

Version updated for https://github.com/MattJColes/lgtmaybe to version lgtmaybe-v1.14.0. This action is used across all versions by ? repositories. Action Type This is a Composite action. Go to the GitHub Marketplace to find the latest changes. Action Summary This GitHub Action, lgtmaybe, automates code reviews by analyzing pull request diffs using an OpenAI-compatible model. It identifies logic and correctness bugs, security vulnerabilities, missing tests, outdated or incorrect code, performance regressions, unnecessary complexity, intent misalignment, and potential “ponytail” code. The tool does not run the code but relies on context from surrounding lines in files to provide detailed reviews, reducing false positives.