(thanks to Nutlopes for developing most of this, but I wanted to keep it updated with newer models and some quality of life changes)
The minimum supported version of Node.js is the latest v14. Check your Node.js version with
node --version.
-
Install comai:
npm install -g comai
-
Retrieve your API key from OpenAI
Note: If you haven't already, you'll have to create an account and set up billing.
-
Set the key so comai can use it:
comai config set OPENAI_KEY=<your token>
This will create a
.comaifile in your home directory.
Check the installed version with:
comai --version
If it's not the latest version, run:
npm update -g comaiYou can call comai directly to generate a commit message for your staged changes:
git add <files...>
comaicomai passes down unknown flags to git commit, so you can pass in commit flags.
For example, you can stage all changes in tracked files with as you commit:
comai --all # or -aSometimes the recommended commit message isn't the best so you want it to generate a few to pick from. You can generate multiple commit messages at once by passing in the --generate <i> flag, where 'i' is the number of generated messages:
comai --generate <i> # or -g <i>Warning: this uses more tokens, meaning it costs more.
If you'd like to generate Conventional Commits, you can use the --type flag followed by conventional. This will prompt comai to format the commit message according to the Conventional Commits specification:
comai --type conventional # or -t conventionalThis feature can be useful if your project follows the Conventional Commits standard or if you're using tools that rely on this commit format.
You can also integrate comai with Git via the prepare-commit-msg hook. This lets you use Git like you normally would, and edit the commit message before committing.
In the Git repository you want to install the hook in:
comai hook installIn the Git repository you want to uninstall the hook from:
comai hook uninstall-
Stage your files and commit:
git add <files...> git commit # Only generates a message when it's not passed in
If you ever want to write your own message instead of generating one, you can simply pass one in:
git commit -m "My message" -
Comai will generate the commit message for you and pass it back to Git. Git will open it with the configured editor for you to review/edit it.
-
Save and close the editor to commit!
You can set persistent CLI options so you don't have to specify flags every time you run comai.
comai options
# or
comai options showcomai options set all=true
comai options set generate=3
comai options set type=conventional
comai options set exclude=package-lock.json,dist/comai options get all
comai options get generatecomai options clear all
comai options clear generate- all:
true|false- Automatically stage all tracked files (equivalent to--allflag) - exclude:
file1,file2- Comma-separated list of files to exclude (equivalent to--excludeflag) - generate:
1-5- Number of commit messages to generate (equivalent to--generateflag) - type:
conventional- Type of commit message format (equivalent to--typeflag)
Once you set options, comai will use them as defaults every time you run it. CLI flags will always override stored options.
For example:
# Set preferences
comai options set all=true generate=2
# This will use your stored preferences
comai
# This will override the stored generate setting for this run only
comai --generate 5To retrieve a configuration option, use the command:
comai config get <key>For example, to retrieve the API key, you can use:
comai config get OPENAI_KEYYou can also retrieve multiple configuration options at once by separating them with spaces:
comai config get OPENAI_KEY generateTo set a configuration option, use the command:
comai config set <key>=<value>For example, to set the API key, you can use:
comai config set OPENAI_KEY=<your-api-key>You can also set multiple configuration options at once by separating them with spaces, like
comai config set OPENAI_KEY=<your-api-key> generate=3 locale=enRequired
The OpenAI API key. You can retrieve it from OpenAI API Keys page.
Default: en
The locale to use for the generated commit messages. Consult the list of codes in: https://wikipedia.org/wiki/List_of_ISO_639-1_codes.
Default: 1
The number of commit messages to generate to pick from.
Note, this will use more tokens as it generates more results.
Set a HTTP/HTTPS proxy to use for requests.
To clear the proxy option, you can use the command (note the empty value after the equals sign):
comai config set proxy=Default: gpt-5
The Chat Completions (/v1/chat/completions) model to use. Consult the list of models available in the OpenAI Documentation.
Tip: The default model is now
gpt-5. You can also usegpt-4or other models if needed. Check out OpenAI's website to learn more about model capabilities and pricing.
The timeout for network requests to the OpenAI API in milliseconds.
Default: 10000 (10 seconds)
comai config set timeout=20000 # 20sThe maximum character length of the generated commit message.
Default: 50
comai config set max-length=100Default: "" (Empty string)
The type of commit message to generate. Set this to "conventional" to generate commit messages that follow the Conventional Commits specification:
comai config set type=conventionalYou can clear this option by setting it to an empty string:
comai config set type=This CLI tool runs git diff to grab all your latest code changes, sends them to OpenAI's GPT-5, then returns the AI generated commit message.
Video coming soon where I rebuild it from scratch to show you how to easily build your own CLI tools powered by AI.
- Ryan Vogel: @R44VC0RP
If you want to help fix a bug or implement a feature in Issues, checkout the Contribution Guide to learn how to setup and test the project