AICommit2

A Reactive CLI that generates git commit messages with Ollama, ChatGPT, Gemini, Claude, Mistral and other AI

Introduction

aicommit2 streamlines interactions with various AI, enabling users to request multiple AI simultaneously and select the most suitable commit message without waiting for all AI responses. The core functionalities and architecture of this project are inspired by AICommits.

Supported Providers

Remote

• OpenAI
• Anthropic Claude
• Gemini
• Mistral AI
  • Codestral (Free till August 1, 2024)
• Cohere
• Groq
• Huggingface (Unofficial)
• Clova X (Unofficial)

Local

• Ollama

Setup

The minimum supported version of Node.js is the v18. Check your Node.js version with node --version.

1. Install aicommit2:

npm install -g aicommit2

2. Retrieve and set API keys or Cookie you intend to use:

It is not necessary to set all keys. But at least one key must be set up.

• OpenAI

aicommit2 config set OPENAI_KEY=<your key>

• Anthropic Claude

aicommit2 config set ANTHROPIC_KEY=<your key>

• Gemini

aicommit2 config set GEMINI_KEY=<your key>

• Mistral AI

aicommit2 config set MISTRAL_KEY=<your key>

• Codestral

aicommit2 config set CODESTRAL_KEY=<your key>

• Cohere

aicommit2 config set COHERE_KEY=<your key>

• Groq

aicommit2 config set GROQ_KEY=<your key>

• Huggingface (Unofficial)

# Please be cautious of Escape characters(\", \') in browser cookie string 
aicommit2 config set HUGGING_COOKIE="<your browser cookie>"

• Clova X (Unofficial)

# Please be cautious of Escape characters(\", \') in browser cookie string 
aicommit2 config set CLOVAX_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.

3. Run aicommit2 with your staged files in git repository:

git add <files...>
aicommit2

Using Locally

You can also use your model for free with Ollama and it is available to use both Ollama and remote providers simultaneously.

1. Install Ollama from https://ollama.com

2. Start it with your model

ollama run llama3 # model you want use. ex) codellama, deepseek-coder

3. Set the model and host

aicommit2 config set OLLAMA_MODEL=<your model>

If you want to use ollama, you must set OLLAMA_MODEL.

4. Run aicommit2 with your staged in git repository

git add <files...>
aicommit2

👉 Tip: Ollama can run LLMs in parallel from v0.1.33. Please see this section.

How it works

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.

Usage

CLI mode

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 aic2 alias if aicommit2 is too long for you.

CLI Options

--locale or -l

• Locale to use for the generated commit messages (default: en)

aicommit2 --locale <s> # or -l <s>

--generate or -g

• Number of messages to generate (Warning: generating multiple costs more) (default: 1)
• Sometimes 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:

aicommit2 --generate <i> # or -g <i>

Warning: this uses more tokens, meaning it costs more.

--all or -a

• Automatically stage changes in tracked files for the commit (default: false)

aicommit2 --all # or -a

--type or -t

• Automatically stage changes in tracked files for the commit (default: conventional)
• it supports conventional and gitmoji

aicommit2 --type conventional # or -t conventional
aicommit2 --type gitmoji # or -t gitmoji

--confirm or -y

• Skip confirmation when committing after message generation (default: false)

aicommit2 --confirm # or -y

--clipboard or -c

• Copy the selected message to the clipboard (default: false)
• This is a useful option when you don't want to commit through aicommit2.
• If you give this option, aicommit2 will not commit.

aicommit2 --clipboard # or -c

--prompt or -p

• Additional prompt to let users fine-tune provided prompt

aicommit2 --prompt <s> # or -p <s>

Git hook

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.

Install

In the Git repository you want to install the hook in:

aicommit2 hook install

Uninstall

In the Git repository you want to uninstall the hook from:

aicommit2 hook uninstall

Usage

1. 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"

2. 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.

3. Save and close the editor to commit!

Configuration

Reading a configuration value

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 

Setting a configuration value

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

Options

Currently, options are set universally. However, there are plans to develop the ability to set individual options in the future.

Available Options by Model

Common Options

locale

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.

generate

Default: 1

The number of commit messages to generate to pick from.

Note, this will use more tokens as it generates more results.

proxy

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=

timeout

The timeout for network requests to the OpenAI API in milliseconds.

Default: 10_000 (10 seconds)

aicommit2 config set timeout=20000 # 20s

max-length

The maximum character length of the generated commit message.

Default: 50

aicommit2 config set max-length=100

type

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=

max-tokens

The maximum number of tokens that the AI models can generate.

Default: 200

aicommit2 config set max-tokens=1000

temperature

The temperature (0.0-2.0) is used to control the randomness of the output

Default: 0.7

aicommit2 config set temperature=0

prompt

Additional prompt to let users fine-tune provided prompt. Users provide extra instructions to AI and can guide how commit messages should look like.

aicommit2 config set prompt="Do not mention config changes"

logging

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).

• You can remove all logs below comamnd.

aicommit2 log removeAll 

Ollama

OLLAMA_MODEL

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

OLLAMA_HOST

Default: http://localhost:11434

The Ollama host

aicommit2 config set OLLAMA_HOST=<host>

OLLAMA_TIMEOUT

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>

OLLAMA_STREAM

Default: false

Determines whether the application will make stream requests to Ollama. Allow this option only when using Ollama alone.

This feature is experimental and may not be fully stable.

OPEN AI

OPENAI_KEY

The OpenAI API key. You can retrieve it from OpenAI API Keys page.

OPENAI_MODEL

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-4 for 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

OPENAI_URL

Default: https://api.openai.com

The OpenAI URL. Both https and http protocols supported. It allows to run local OpenAI-compatible server.

OPENAI_PATH

Default: /v1/chat/completions

The OpenAI Path.

Anthropic Claude

ANTHROPIC_KEY

The Anthropic API key. To get started with Anthropic Claude, request access to their API at anthropic.com/earlyaccess.

ANTHROPIC_MODEL

Default: claude-3-haiku-20240307

Supported:

• claude-3-haiku-20240307
• claude-3-sonnet-20240229
• claude-3-opus-20240229
• claude-2.1
• claude-2.0
• claude-instant-1.2

aicommit2 config set ANTHROPIC_MODEL=claude-instant-1.2

GEMINI

GEMINI_KEY

The Gemini API key. If you don't have one, create a key in Google AI Studio.

GEMINI_MODEL

Default: gemini-1.5-pro-latest

Supported:

• gemini-1.5-pro-latest
• gemini-1.5-flash-latest

The models mentioned above are subject to change.

MISTRAL

MISTRAL_KEY

The Mistral API key. If you don't have one, please sign up and subscribe in Mistral Console.

MISTRAL_MODEL

Default: mistral-tiny

Supported:

• open-mistral-7b
• mistral-tiny-2312
• mistral-tiny
• open-mixtral-8x7b
• mistral-small-2312
• mistral-small
• mistral-small-2402
• mistral-small-latest
• mistral-medium-latest
• mistral-medium-2312
• mistral-medium
• mistral-large-latest
• mistral-large-2402
• mistral-embed
• codestral-latest
• codestral-2405

The models mentioned above are subject to change.

CODESTRAL

CODESTRAL_KEY

The Codestral API key. If you don't have one, please sign up and subscribe in Mistral Console.

CODESTRAL_MODEL

Default: codestral-latest

Supported:

• codestral-latest
• codestral-2405

The models mentioned above are subject to change.

Cohere

COHERE_KEY

The Cohere API key. If you don't have one, please sign up and get the API key in Cohere Dashboard.

COHERE_MODEL

Default: command

Supported:

• command
• command-nightly
• command-light
• command-light-nightly

The models mentioned above are subject to change.

Groq

GROQ_KEY

The Groq API key. If you don't have one, please sign up and get the API key in Groq Console.

GROQ_MODEL

Default: gemma-7b-it

Supported:

• llama3-8b-8192
• 'llama3-70b-8192'
• mixtral-8x7b-32768
• gemma-7b-it

The models mentioned above are subject to change.

HuggingFace Chat

HUGGING_COOKIE

The Huggingface Chat Cookie. Please check how to get cookie

HUGGING_MODEL

Default: mistralai/Mixtral-8x7B-Instruct-v0.1

Supported:

• CohereForAI/c4ai-command-r-plus
• meta-llama/Meta-Llama-3-70B-Instruct
• HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1
• mistralai/Mixtral-8x7B-Instruct-v0.1
• NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO
• google/gemma-1.1-7b-it
• mistralai/Mistral-7B-Instruct-v0.2
• microsoft/Phi-3-mini-4k-instruct

The models mentioned above are subject to change.

Clova X

CLOVAX_COOKIE

The Clova X Cookie. Please check how to get cookie

Upgrading

Check the installed version with:

aicommit2 --version

If it's not the latest version, run:

npm update -g aicommit2

Loading Multiple Ollama Models

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 simultaneously

Setup Guide

Follow these steps to set up and utilize multiple models simultaneously:

1. Running Ollama Server

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.

2. Configuring aicommit2

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.

3. Run aicommit2

aicommit2

Note that this feature is available starting from Ollama version 0.1.33 and aicommit2 version 1.9.5.

How to get Cookie(Unofficial API)

• Login to the site you want
• You can get cookie from the browser's developer tools network tab
• See for any requests check out the Cookie, Copy whole value
• Check below image for the format of cookie

When setting cookies with long string values, ensure to escape characters like ", ', and others properly.

• For double quotes ("), use \"
• For single quotes ('), use \'

Disclaimer

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.

Risk Acknowledgment

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.

Please Star ⭐️

If this project has been helpful to you, I would greatly appreciate it if you could click the Star⭐️ button on this repository!

Maintainers

• @tak-bro

Contributing

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.

Contributors ✨

Thanks goes to these wonderful people (emoji key):

@eltociear 📖

@ubranch 💻

@bhodrolok 💻