better

A code reviewer github action powered by AI, ready to be used in your workflow.

https://www.producthunt.com/posts/better-code-reviewer-powered-by-ai?embed=true&utm_source=badge-featured&utm_medium=badge&utm_souce=badge-better-code-reviewer-powered-by-ai

Why use it?

Usage

1. Create a workflow

Create a workflow file inside .github/workflows folder (create if it doesn’t exist) of your repository with the following content:

name: Code Review
on:
    pull_request:
        types: [opened, reopened, synchronize, ready_for_review]
        branches:
            - main # change this to your target branch
    workflow_dispatch: # Allows you to run the workflow manually from the Actions tab

permissions: # necessary permissions
    pull-requests: write
    contents: read

jobs:
    your-job-name:
        runs-on: ubuntu-latest
        name: your-job-name
        steps:
            - name: step-name
              id: step-id
              uses: murtuzaalisurti/better@v3 # this is the ref of the github action - https://docs.github.com/en/actions/writing-workflows/workflow-syntax-for-github-actions#jobsjob_iduses
              with:
                repo-token: $ # this is auto generated
                ai-model-api-key: $ # make sure to set this in your repository secrets - /settings/secrets/actions (Settings > Secrets and Variables > Actions > Secrets Tab)
                platform: 'openai' # can be 'openai' | 'anthropic' | 'google' | 'openrouter' | 'mistral'
                delete-existing-review-by-bot: true #default is true
                filesToIgnore: '**/*.env; .husky/**; .cache/**' # uses glob patterns (micromatch - https://github.com/micromatch/micromatch)
                rules: |- # Rules to consider for code review
                    -- It must follow industry standard best practices
                    -- It should be idiomatic
                    -- It should be readable
                    -- It should not contain any security related vulnerabilities
                    -- It should not contain any sensitive data
                    -- It should be well structured
                    -- It should not contain bad patterns

[!NOTE] The uses field refers to which github action to use and what’s its reference. For example: murtuzaalisurti/better@main means it refers to the main branch of the murtuzaalisurti/better action. If you want to refer to a specific release or tag, you can specify murtuzaalisurti/better@v1.0.0 which means it refers to the v1.0.0 of the murtuzaalisurti/better action.

2. Add your platform API key to your repository secrets

Go to your repository settings, Settings > Secrets and Variables > Actions > Secrets Tab and add your platform API key. For example, add OPEN_AI_KEY as a secret with your OpenAI API key as a value. You can refer to it in the workflow file using $ against the ai-model-api-key field.

repo-settings-page

3. Grant permissions

repo-settings-permissions-actions

4. Run the workflow

Run the workflow by raising a pull request to the target branch mentioned in the on section in the workflow.

Options

1. repo-token

The repo-token is the authorization token of your repository. It is auto generated by GitHub on every workflow run.

2. platform

The platform is the name of the AI platform you want to use. It can be either openai or anthropic or google or mistral or openrouter.

This action supports *OpenAI, Anthropic, Gemini, Mistral and Deepseek models*.

3. ai-model-api-key

The ai-model-api-key is your platform’s API key which you have set in your repository secrets.

Example:

They can be accessed in the workflow file using $.

4. ai-model-name (Optional)

Specify the name of the model you want to use to generate suggestions. Fallbacks to gpt-5 for OpenAI, claude-3-7-sonnet-latest for Anthropic, gemini-2.5-pro-preview-06-05 for Google’s Gemini, pixtral-12b-2409 for Mistral, and google/gemini-2.5-pro-preview-06-05 for OpenRouter if not specified. Here’s a list of supported models:

For OpenAI:

This project uses Structured Outputs and that’s why only the above listed models are supported. More info here.

For Anthropic:

For Mistral:

For OpenRouter:

For Google:

5. delete-existing-review-by-bot (Optional)

By default, the action will delete any existing review(s) by the bot before creating a new one on every PR push. If you want to keep them, set this option to false.

6. rules (Optional)

The rules to consider for code review. It is a multiline text field. Each rule should be on a new line and should start with --.

7. filesToIgnore (Optional)

List of files to ignore. It is a semicolon(;) separated list of glob patterns. The default list of ignored files is:

**/node_modules/**
**/package-lock.json
**/yarn.lock
.cache/**
**/*.{jpg,jpeg,png,svg,webp,avif,gif,ico,woff,woff2,ttf,otf}

Glob patterns are resolved using micromatch. Check out their documentation for more info.

8. max-retries (Optional)

The maximum number of retries the action will perform on failure while generating suggestions from the AI model. Specify 0 to skip retries (see things to note below to know why this is important). The default value is 3 if you don’t specify.

Things To Note

Made with ❤️ by @murtuzaalisurti. Learn more at https://syntackle.com/blog/ai-powered-code-review-tool-better/.