git-bob 0.2.7

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

git-bob

git-bob uses AI to solve Github-issues and review pull-requests. It runs inside the Github CI, no need to install anything on your computer.

Under the hood it uses Anthropic's Claude or OpenAI's chatGPT 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 Anthropic, OpenAI or any other endpoint via git-bob, you are bound to the terms of service of the respective companies or organizations. The github issues, pull-requests and messages 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

There is a detailed tutorial on how to install git-bob as github action to your repository. In very short, 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==0.2.2.
  • Configure the LLM you want to use in the workflow files by specifying the GIT_BOB_LLM_NAME environment variable. These were tested:
• claude-3-5-sonnet-20240620
• gpt-4o-2024-08-06 (recommended if you work with large files, < 16k tokens)

• configure a Github secret called OPENAI_API_KEY or ANTHROPIC_API_KEY with the corresponding key from the LLM provider depending on the above configured LLM. You can get these keys here:
  • OpenAI (gpt)
  • Anthropic (claude)
• configure Github actions to run the workflow on issues and pull-requests. Also give write-access to the Workflow using the GITHUB_TOKEN.

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

git-bob comment

If the issue is complex and should be split into sub-issues, you can use the following command:

git-bob split

You can also use the following command to trigger git-bob solving an issue. It will then try to solve the issue and send a pull-request.

git-bob solve

Recommended Workflow

Here's the recommended workflow for using git-bob:

1. Create an issue describing the problem or task.
2. Comment on the issue with git-bob comment, or git-bob think about this (an alias for comment) to trigger git-bob making a plan.
3. Respond to git-bob with any clarifications or additional information it requests.
4. Comment on the issue with git-bob solve or git-bob implement this (an alias for solve) to trigger git-bob.
5. Wait for git-bob to create a pull request (PR) addressing the issue.
6. Review the PR and comment on the issue if changes are needed.
7. Wait for git-bob to create a second PR with the requested changes.
8. Repeat steps 3-5 as necessary until the issue is resolved satisfactorily.

Use-case examples

Solving github issues

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

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

Review Pull-Requests

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

Splitting Issues

To split a main issue into sub-issues, ask git-bob split this issue.

General prompting

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
• split-issue

Limitations

git-bob is a research project and has limitations. It serves as basis for discussion and further development. Once LLMs become better, git-bob will become better as well.

At the moment, these limitations can be observed:

• git-bob was tested for Python projects only (yet).
• It sometimes halucinates, especially in code reviews. E.g. it claimed to have tested code, which is certainly not true.
• It cannot solve issues where changing long files is required, as the output of the LLMs is limited by a maximum number of tokens (e.g. 16k for gpt-4o-2024-08-06).
• It cannot solve issues where running and testing the code is required.
• When changing multiple files, it may introduce conflicts between the files, as it does not know about the content of the other files.
• It has only limited logic to control who is allowed to trigger it. If you are a repository member, you can trigger it. If others send a pull-request, a repository member must allow the action to run manually.
• git-bob is incompatible with locally running open-source/-weight LLMs. This might make sense when being executed locally only. In the Github-CI this might be impossible.
• Recently tested claude-3-5-sonnet-20240620 and gpt-4o-2024-08-06 models produce useful results. The model gemini-1.5-flash-001 is technically supported too, but its results were not very useful.

Similar projects

There are similar projects out there

• Claude Engineer
• BioChatter
• aider
• OpenDevin
• Devika
• GPT-Codemaster
• Github Copilot Workspace
• agentless

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