git-bob 0.1.0

An AI-based assistant for handling github issues and pull-requests

git-bob

git-bob uses AI to answer Github-issues and review pull-requests.

Under the hood it uses claude 3.5 sonnet or gpt-4 omni to understand the text and pygithub to interact with the issues and pull-requests.

Disclaimer

git-bob is a research project aiming at streamlining Github interaction in software development projects. Under the hood it uses artificial intelligence / large language models to generate text and code fulfilling the user's requests. Users are responsible to verify the generated code according to good scientific practice.

When using git-bob you configure it to use an API key to access the AI models. You have to pay for the usage and must be careful in using the software. Do not use this technology if you are not aware of the costs and consequences.

[!CAUTION] When using the OpenAI, Google Gemini, Anthropic or any other endpoint via git-bob, you are bound to the terms of service of the respective companies or organizations. The prompts you enter are transferred to their servers and may be processed and stored there. Make sure to not submit any sensitive, confidential or personal data. Also using these services may cost money.

Installation as Github action

To use git-bob in your Github repository, you need to

• setup Github workflows like shown in this folder.
  • Make sure to replace pip install -e . with a specific git-bob version such as pip install git-bob==0.1.0.
  • Configure the LLM you want to use in the workflow files by specifying the GIT_BOB_LLM_NAME environment variable.
• configure a Github secret called ANTHROPIC_API_KEY or an OPENAI_API_KEY depending on the above configured LLM.
• configure Github actions to run the workflow on issues and pull-requests. Also give write-access to the action runner.

To trigger git-bob, you need to comment on an issue or pull-request with the following command:

git-bob comment

When using openai/gpt-4-omni, you can also use the following command to trigger git-bob. It will then try to solve the issue and send a pull-request.

git-bob solve

Note: This will only work with simple issues that can be solved by modifying a single file.

Use-case examples

• git-bob can fix typos (issue, pull-request):

• git-bob can improve code documentation (issue, pull-request):

• git-bob can review pull-requests and provide feedback (pull-request):

• git-bob can also be exploited to answer questions (issue).

Installation as command-line tool

You can also install git-bob locally and run it from the terminal. In this case, create a Github token and store it in an environment variable named GITHUB_API_KEY. Also create an environment variable GIT_BOB_LLM_NAME with the name of the LLM you want to use, e.g. "gpt-4o-2024-05-13" or "claude-3-5-sonnet-20240620". Then you can install git-bob using pip:

pip install git-bob

Usage as command-line tool

You can then use git-bob from the terminal on repositories you have read/write access to.

git_bob <action> <organization>/<repository> <issue-number>

Available actions:

• review-pull-request
• comment-on-issue
• solve-issue (only works with OpenAI/gpt-4-omni at the moment)

Limitations

• git-bob was tested for Python projects only (yet).
• It cannot solve issues where changing multiple files is required.
• It does not have any logic to control who is allowed to trigger it. It uses Github infrastructure instead. Hence, if you are a repository member, you can trigger it. If others send a pull-request, some repository member must allow the action to run manually.
• git-bob is not compatible with locally running open-source/weight LLMs. This might make sense when being executed locally only. In the Github-CI this might be impossible.

Similar projects

There are similar projects out there

• Claude Engineer
• BioChatter
• aider
• OpenDevin
• Devika
• GPT-Codemaster

Contributing

Feedback and contributions are welcome! Just open an issue and let's discuss before you send a pull-request. A human will respond and comment on your ideas!

Acknowledgements

We acknowledge the financial support by the Federal Ministry of Education and Research of Germany and by Sächsische Staatsministerium für Wissenschaft, Kultur und Tourismus in the programme Center of Excellence for AI-research „Center for Scalable Data Analytics and Artificial Intelligence Dresden/Leipzig“, project identification number: ScaDS.AI