Skip to main content

Add your description here

Project description

gut

Trust your guts on git🫀

gut is an AI-powered CLI tool that executes all the git/gh commands you want from natural language queries.

Set-up and Execution

User settings

gut is available as a python package, and cna be easily installed with:

pip install gut-ai

You then just need to set GROQ_API_KEY as an environment variable, either exporting it on the console or in a .env file in the root folder where you are executing gut, and then you can simply launch it via:

gut-ai

Developer settings

You can clone this repository:

git clone https://github.com/AstraBert/gut
cd gut/

And then install the needed dependencies with uv:

uv sync

You then just need to set GROQ_API_KEY as an environment variable, either exporting it on the console or in a .env file in the root folder where you are executing gut, and then you can simply launch it via:

uvx --from . gut-ai

How Does It Work?

gut leverages an AI-powered workflow (designed with llama-index-workflows), whose steps are:

  • Choose the main command to execute between git and gh based on the user's requirements
  • Choose the command/subcommand and options to employ with the main command (e.g. add . for git if the user asked to add local changes to git)
  • Produce an explanation for the command
  • Expose the command and the explanation to the user, asking fot their feedback (human-in-the-loop or HITL approach).
  • If the feedback is positive, the command gets executed, otherwise the workflow restarts from the beginning, re-using the initial instructions and the feedback that the user provided.

The whole workflow runs in a Rich console and leverages structured inputs (through XML/JSON representations of Pydantic models) and outputs.

Contributing

Contributions are always welcome - make sure to read the contributions guide before submitting yours!

License

This project is provided under an MIT License.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

gut_ai-0.1.0.post1.tar.gz (71.6 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

gut_ai-0.1.0.post1-py3-none-any.whl (9.4 kB view details)

Uploaded Python 3

File details

Details for the file gut_ai-0.1.0.post1.tar.gz.

File metadata

  • Download URL: gut_ai-0.1.0.post1.tar.gz
  • Upload date:
  • Size: 71.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.8.0

File hashes

Hashes for gut_ai-0.1.0.post1.tar.gz
Algorithm Hash digest
SHA256 a374344bb5e600bf2c3a8f4abf52c185934abf371e6c679d46d48eb3cc92204e
MD5 577ae398bcafb0bc36d135a8860d256b
BLAKE2b-256 cb7c1899774b9343dec196b454a7995c55e0a553a8a2ca7f62e3566ca33c338c

See more details on using hashes here.

File details

Details for the file gut_ai-0.1.0.post1-py3-none-any.whl.

File metadata

File hashes

Hashes for gut_ai-0.1.0.post1-py3-none-any.whl
Algorithm Hash digest
SHA256 3913f7d5313838f967bdcb384911e9bccd16f8d3725099818429d9b6ab941834
MD5 69a04fe22810952a03a906e7cc67e564
BLAKE2b-256 197f322317d6be0af1097ef903898907a8f8174a67034be4339f20e535acc7ef

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page