@f97/aicommit2
Advanced tools
A Reactive CLI that generates git commit messages with Ollama, ChatGPT, Gemini, Claude, Mistral and other AI
aicommit2 is a reactive CLI tool that automatically generates Git commit messages using various AI models. It supports simultaneous requests to multiple AI providers, allowing users to select the most suitable commit message. The core functionalities and architecture of this project are inspired by AICommits.
The minimum supported version of Node.js is the v18. Check your Node.js version with
node --version.
npm install -g aicommit2
It is not necessary to set all keys. But at least one key must be set up.
aicommit2 config set OPENAI_KEY=<your key>
aicommit2 config set ANTHROPIC_KEY=<your key>
aicommit2 config set GEMINI_KEY=<your key>
aicommit2 config set MISTRAL_KEY=<your key>
aicommit2 config set CODESTRAL_KEY=<your key>
aicommit2 config set COHERE_KEY=<your key>
aicommit2 config set GROQ_KEY=<your key>
# Please be cautious of Escape characters(\", \') in browser cookie string
aicommit2 config set HUGGINGFACE_COOKIE="<your browser cookie>"
This will create a .aicommit2 file in your home directory.
You may need to create an account and set up billing.
git add <files...>
aicommit2
You can also use your model for free with Ollama and it is available to use both Ollama and remote providers simultaneously.
Install Ollama from https://ollama.com
Start it with your model
ollama run llama3 # model you want use. ex) codellama, deepseek-coder
aicommit2 config set OLLAMA_MODEL=<your model>
If you want to use ollama, you must set OLLAMA_MODEL.
git add <files...>
aicommit2
👉 Tip: Ollama can run LLMs in parallel from v0.1.33. Please see this section.
This CLI tool runs git diff to grab all your latest code changes, sends them to configured AI, then returns the AI generated commit message.
If the diff becomes too large, AI will not function properly. If you encounter an error saying the message is too long or it's not a valid commit message, try reducing the commit unit.
You can call aicommit2 directly to generate a commit message for your staged changes:
git add <files...>
aicommit2
aicommit2 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:
aicommit2 --all # or -a
👉 Tip: Use the
aic2alias ifaicommit2is too long for you.
--locale or -laicommit2 --locale <s> # or -l <s>
--generate or -g--generate <i> flag, where 'i' is the number of generated messages:aicommit2 --generate <i> # or -g <i>
Warning: this uses more tokens, meaning it costs more.
--all or -aaicommit2 --all # or -a
--type or -tconventional and gitmojiaicommit2 --type conventional # or -t conventional
aicommit2 --type gitmoji # or -t gitmoji
--confirm or -yaicommit2 --confirm # or -y
--clipboard or -caicommit2 --clipboard # or -c
--promptPath or -paicommit2 --promptPath <s> # or -p <s>
You can also integrate aicommit2 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:
aicommit2 hook install
In the Git repository you want to uninstall the hook from:
aicommit2 hook uninstall
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"
aicommit2 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!
To retrieve a configuration option, use the command:
aicommit2 config get <key>
For example, to retrieve the API key, you can use:
aicommit2 config get OPENAI_KEY
You can also retrieve multiple configuration options at once by separating them with spaces:
aicommit2 config get OPENAI_KEY OPENAI_MODEL GEMINI_KEY
To set a configuration option, use the command:
aicommit2 config set <key>=<value>
For example, to set the API key, you can use:
aicommit2 config set OPENAI_KEY=<your-api-key>
You can also set multiple configuration options at once by separating them with spaces, like
aicommit2 config set OPENAI_KEY=<your-api-key> generate=3 locale=en
| Option | Default | Description |
|---|---|---|
OPENAI_KEY | N/A | The OpenAI API key |
OPENAI_MODEL | gpt-3.5-turbo | The OpenAI Model to use |
OPENAI_URL | https://api.openai.com | The OpenAI URL |
OPENAI_PATH | /v1/chat/completions | The OpenAI request pathname |
ANTHROPIC_KEY | N/A | The Anthropic API key |
ANTHROPIC_MODEL | claude-3-haiku-20240307 | The Anthropic Model to use |
GEMINI_KEY | N/A | The Gemini API key |
GEMINI_MODEL | gemini-1.5-pro-latest | The Gemini Model |
MISTRAL_KEY | N/A | The Mistral API key |
MISTRAL_MODEL | mistral-tiny | The Mistral Model to use |
CODESTRAL_KEY | N/A | The Codestral API key |
CODESTRAL_MODEL | codestral-latest | The Codestral Model to use |
COHERE_KEY | N/A | The Cohere API Key |
COHERE_MODEL | command | The identifier of the Cohere model |
GROQ_KEY | N/A | The Groq API Key |
GROQ_MODEL | gemma-7b-it | The Groq model name to use |
HUGGINGFACE_COOKIE | N/A | The HuggingFace Cookie string |
HUGGINGFACE_MODEL | mistralai/Mixtral-8x7B-Instruct-v0.1 | The HuggingFace Model to use |
OLLAMA_MODEL | N/A | The Ollama Model. It should be downloaded your local |
OLLAMA_HOST | http://localhost:11434 | The Ollama Host |
OLLAMA_TIMEOUT | 100_000 ms | Request timeout for the Ollama |
locale | en | Locale for the generated commit messages |
generate | 1 | Number of commit messages to generate |
type | conventional | Type of commit message to generate |
proxy | N/A | Set a HTTP/HTTPS proxy to use for requests(only OpenAI) |
timeout | 10_000 ms | Network request timeout |
max-length | 50 | Maximum character length of the generated commit message(Subject) |
max-tokens | 1024 | The maximum number of tokens that the AI models can generate (for Open AI, Anthropic, Gemini, Mistral, Codestral) |
temperature | 0.7 | The temperature (0.0-2.0) is used to control the randomness of the output (for Open AI, Anthropic, Gemini, Mistral, Codestral) |
promptPath | N/A | Allow users to specify a custom file path for their own prompt template |
logging | false | Whether to log AI responses for debugging (true or false) |
ignoreBody | false | Whether the commit message includes body (true or false) |
Currently, options are set universally. However, there are plans to develop the ability to set individual options in the future.
| locale | generate | type | proxy | timeout | max-length | max-tokens | temperature | prompt | |
|---|---|---|---|---|---|---|---|---|---|
| OpenAI | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
| Anthropic Claude | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ||
| Gemini | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ||
| Mistral AI | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | |
| Codestral | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | |
| Cohere | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ||
| Groq | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | |||
| Huggingface | ✓ | ✓ | ✓ | ✓ | ✓ | ||||
| Ollama | ✓ | ✓ | ✓ | ⚠ (OLLAMA_TIMEOUT) | ✓ | ✓ | ✓ |
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_language_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):
Only supported within the OpenAI
aicommit2 config set proxy=
The timeout for network requests to the OpenAI API in milliseconds.
Default: 10_000 (10 seconds)
aicommit2 config set timeout=20000 # 20s
The maximum character length of the generated commit message.
Default: 50
aicommit2 config set max-length=100
Default: conventional
Supported: conventional, gitmoji
The type of commit message to generate. Set this to "conventional" to generate commit messages that follow the Conventional Commits specification:
aicommit2 config set type=conventional
You can clear this option by setting it to an empty string:
aicommit2 config set type=
The maximum number of tokens that the AI models can generate.
Default: 1024
aicommit2 config set max-tokens=3000
The temperature (0.0-2.0) is used to control the randomness of the output
Default: 0.7
aicommit2 config set temperature=0
aicommit2 config set promptPath="/path/to/user/prompt.txt"
Default: false
Option that allows users to decide whether to generate a log file capturing the responses.
The log files will be stored in the ~/.aicommit2_log directory(user's home).
aicommit2 config set logging="true"
aicommit2 log removeAll
Default: false
This option determines whether the commit message includes body. If you don't want to include body in message, you can set it to true.
aicommit2 config set ignoreBody="true"
aicommit2 config set ignoreBody="false"
The Ollama Model. Please see a list of models available
aicommit2 config set OLLAMA_MODEL="llama3"
aicommit2 config set OLLAMA_MODEL="llama3,codellama" # for multiple models
Default: http://localhost:11434
The Ollama host
aicommit2 config set OLLAMA_HOST=<host>
Default: 100_000 (100 seconds)
Request timeout for the Ollama. Default OLLAMA_TIMEOUT is 100 seconds because it can take a long time to run locally.
aicommit2 config set OLLAMA_TIMEOUT=<timout>
The OpenAI API key. You can retrieve it from OpenAI API Keys page.
Default: gpt-3.5-turbo
The Chat Completions (/v1/chat/completions) model to use. Consult the list of models available in the OpenAI Documentation.
Tip: If you have access, try upgrading to
gpt-4for next-level code analysis. It can handle double the input size, but comes at a higher cost. Check out OpenAI's website to learn more.
aicommit2 config set OPENAI_MODEL=gpt-4
Default: https://api.openai.com
The OpenAI URL. Both https and http protocols supported. It allows to run local OpenAI-compatible server.
Default: /v1/chat/completions
The OpenAI Path.
The Anthropic API key. To get started with Anthropic Claude, request access to their API at anthropic.com/earlyaccess.
Default: claude-3-haiku-20240307
Supported:
claude-3-haiku-20240307claude-3-sonnet-20240229claude-3-opus-20240229claude-2.1claude-2.0claude-instant-1.2aicommit2 config set ANTHROPIC_MODEL=claude-instant-1.2
The Gemini API key. If you don't have one, create a key in Google AI Studio.
Default: gemini-1.5-pro-latest
Supported:
gemini-1.5-pro-latestgemini-1.5-flash-latestThe models mentioned above are subject to change.
The Mistral API key. If you don't have one, please sign up and subscribe in Mistral Console.
Default: mistral-tiny
Supported:
open-mistral-7bmistral-tiny-2312mistral-tinyopen-mixtral-8x7bmistral-small-2312mistral-smallmistral-small-2402mistral-small-latestmistral-medium-latestmistral-medium-2312mistral-mediummistral-large-latestmistral-large-2402mistral-embedThe models mentioned above are subject to change.
The Codestral API key. If you don't have one, please sign up and subscribe in Mistral Console.
Default: codestral-latest
Supported:
codestral-latestcodestral-2405The models mentioned above are subject to change.
The Cohere API key. If you don't have one, please sign up and get the API key in Cohere Dashboard.
Default: command
Supported:
commandcommand-nightlycommand-lightcommand-light-nightlyThe models mentioned above are subject to change.
The Groq API key. If you don't have one, please sign up and get the API key in Groq Console.
Default: gemma-7b-it
Supported:
llama3-8b-8192mixtral-8x7b-32768gemma-7b-itThe models mentioned above are subject to change.
The Huggingface Chat Cookie. Please check how to get cookie
Default: CohereForAI/c4ai-command-r-plus
Supported:
CohereForAI/c4ai-command-r-plusmeta-llama/Meta-Llama-3-70B-InstructHuggingFaceH4/zephyr-orpo-141b-A35b-v0.1mistralai/Mixtral-8x7B-Instruct-v0.1NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO01-ai/Yi-1.5-34B-Chatmistralai/Mistral-7B-Instruct-v0.2microsoft/Phi-3-mini-4k-instructThe models mentioned above are subject to change.
Check the installed version with:
aicommit2 --version
If it's not the latest version, run:
npm update -g aicommit2
aicommit2 supports custom prompt templates through the promptPath option. This feature allows you to define your own prompt structure, giving you more control over the commit message generation process.
To use a custom prompt template, specify the path to your template file when running the tool:
aicommit2 config set promptPath="/path/to/user/prompt.txt"
Your custom template can include placeholders for various commit options.
Use curly braces {} to denote these placeholders for options. The following placeholders are supported:
Here's an example of how your custom template might look:
Generate a {type} commit message in {locale}.
The message should not exceed {maxLength} characters.
Please provide {generate} messages.
Remember to follow these guidelines:
1. Use the imperative mood
2. Be concise and clear
3. Explain the 'why' behind the change
Please note that the following text will always be appended to the end of your custom prompt:
Provide your response as a JSON array where each element is an object with "subject", "body", and "footer" keys.
The "subject" should include the type, optional scope, and description . If there's no body or footer, use an empty string for those fields.
Example response format:
[
{
"subject": "string",
"body": "string",
"footer": "string"
},
]
This ensures that the output is consistently formatted as a JSON array, regardless of the custom template used.
If the specified file cannot be read or parsed, aicommit2 will fall back to using the default prompt generation logic.
Ensure your template includes all necessary instructions for generating appropriate commit messages.
You can still use all other command-line options in conjunction with promptPath.
By using custom templates, you can tailor the commit message generation to your team's specific needs or coding standards.
NOTE: For the
promptPathoption, set the template path, not the template content
You can load and make simultaneous requests to multiple models using Ollama's experimental feature, the OLLAMA_MAX_LOADED_MODELS option.
OLLAMA_MAX_LOADED_MODELS: Load multiple models simultaneouslyFollow these steps to set up and utilize multiple models simultaneously:
First, launch the Ollama server with the OLLAMA_MAX_LOADED_MODELS environment variable set. This variable specifies the maximum number of models to be loaded simultaneously.
For example, to load up to 3 models, use the following command:
OLLAMA_MAX_LOADED_MODELS=3 ollama serve
Refer to configuration for detailed instructions.
Next, set up aicommit2 to specify multiple models. You can assign a list of models, separated by commas(,), to the OLLAMA_MODEL environment variable. Here's how you do it:
aicommit2 config set OLLAMA_MODEL="mistral,dolphin-llama3"
With this command, aicommit2 is instructed to utilize both the "mistral" and "dolphin-llama3" models when making requests to the Ollama server.
aicommit2
Note that this feature is available starting from Ollama version 0.1.33 and aicommit2 version 1.9.5.
When setting cookies with long string values, ensure to escape characters like ", ', and others properly.
- For double quotes ("), use \"
- For single quotes ('), use \'
This project utilizes certain functionalities or data from external APIs, but it is important to note that it is not officially affiliated with or endorsed by the providers of those APIs. The use of external APIs is at the sole discretion and risk of the user.
Users are responsible for understanding and abiding by the terms of use, rate limits, and policies set forth by the respective API providers. The project maintainers cannot be held responsible for any misuse, downtime, or issues arising from the use of the external APIs.
It is recommended that users thoroughly review the API documentation and adhere to best practices to ensure a positive and compliant experience.
If this project has been helpful to you, I would greatly appreciate it if you could click the Star⭐️ button on this repository!
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.
Thanks goes to these wonderful people (emoji key):
 @eltociear 📖 |  @ubranch 💻 |  @bhodrolok 💻 |
FAQs
A Reactive CLI that generates git commit messages with various AI
The npm package @f97/aicommit2 receives a total of 9 weekly downloads. As such, @f97/aicommit2 popularity was classified as not popular.
We found that @f97/aicommit2 demonstrated a not healthy version release cadence and project activity because the last version was released a year ago. It has 1 open source maintainer collaborating on the project.
Did you know?
Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.
Security News
/Research
Socket detected malicious node-ipc versions with obfuscated stealer/backdoor behavior in a developing npm supply chain attack.
Security News
TeamPCP and BreachForums are promoting a Shai-Hulud supply chain attack contest with a $1,000 prize for the biggest package compromise.
Security News
Packagist urges PHP projects to update Composer after a GitHub token format change exposed some GitHub Actions tokens in CI logs.