{"id":13596098,"url":"https://github.com/tbckr/sgpt","last_synced_at":"2026-03-01T17:11:44.305Z","repository":{"id":87504827,"uuid":"606533120","full_name":"tbckr/sgpt","owner":"tbckr","description":"SGPT is a command-line tool that provides a convenient way to interact with OpenAI models, enabling users to run queries, generate shell commands and produce code directly from the terminal.","archived":false,"fork":false,"pushed_at":"2026-02-18T16:43:41.000Z","size":1986,"stargazers_count":415,"open_issues_count":6,"forks_count":34,"subscribers_count":4,"default_branch":"main","last_synced_at":"2026-02-18T19:57:22.317Z","etag":null,"topics":["anthropic","anthropic-claude","bash","cli","gemini","gemini-api","gemini-pro","go","gpt-3","gpt-4","gpt-4-vision","gpt-4-vision-preview","gpt-4o","o1-mini","o1-preview","openai","openrouter","openrouter-api","shell"],"latest_commit_sha":null,"homepage":"","language":"Go","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/tbckr.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":"CODEOWNERS","security":"SECURITY.md","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2023-02-25T19:21:49.000Z","updated_at":"2026-02-18T16:46:58.000Z","dependencies_parsed_at":"2024-01-19T19:25:01.595Z","dependency_job_id":"553011de-bb50-4834-bdd8-20f5b45013ac","html_url":"https://github.com/tbckr/sgpt","commit_stats":null,"previous_names":[],"tags_count":55,"template":false,"template_full_name":null,"purl":"pkg:github/tbckr/sgpt","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tbckr%2Fsgpt","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tbckr%2Fsgpt/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tbckr%2Fsgpt/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tbckr%2Fsgpt/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/tbckr","download_url":"https://codeload.github.com/tbckr/sgpt/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tbckr%2Fsgpt/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29976272,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-01T16:35:47.903Z","status":"ssl_error","status_checked_at":"2026-03-01T16:35:44.899Z","response_time":124,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["anthropic","anthropic-claude","bash","cli","gemini","gemini-api","gemini-pro","go","gpt-3","gpt-4","gpt-4-vision","gpt-4-vision-preview","gpt-4o","o1-mini","o1-preview","openai","openrouter","openrouter-api","shell"],"created_at":"2024-08-01T16:02:08.013Z","updated_at":"2026-03-01T17:11:44.296Z","avatar_url":"https://github.com/tbckr.png","language":"Go","funding_links":[],"categories":["Go","CLIs","CLI and TUI Tools"],"sub_categories":["Codex Resources"],"readme":"# SGPT\n\n[![Release](https://img.shields.io/github/release/tbckr/sgpt.svg?style=for-the-badge)](https://github.com/tbckr/sgpt/releases/latest)\n[![Software License](https://img.shields.io/badge/license-MIT-brightgreen.svg?style=for-the-badge)](/LICENSE.md)\n[![Codecov branch](https://img.shields.io/codecov/c/github/tbckr/sgpt/main.svg?style=for-the-badge)](https://codecov.io/gh/tbckr/sgpt)\n[![Go Report Card](https://goreportcard.com/badge/github.com/tbckr/sgpt/v2?style=for-the-badge)](https://goreportcard.com/report/github.com/tbckr/sgpt/v2)\n[![Go Doc](https://img.shields.io/badge/godoc-reference-blue.svg?style=for-the-badge)](http://godoc.org/github.com/tbckr/sgpt)\n[![Powered By: GoReleaser](https://img.shields.io/badge/powered%20by-goreleaser-green.svg?style=for-the-badge)](https://github.com/goreleaser)\n[![Read the Docs](https://img.shields.io/readthedocs/sgpt?style=for-the-badge)](https://sgpt.readthedocs.io/)\n[![Conventional Commits](https://img.shields.io/badge/Conventional%20Commits-1.0.0-yellow.svg?style=for-the-badge)](https://conventionalcommits.org)\n[![Protected by Gitleaks](https://img.shields.io/badge/protected%20by-gitleaks-blue?style=for-the-badge)](https://github.com/gitleaks/gitleaks-action)\n\nSGPT (*aka shell-gpt*) is a powerful command-line interface (CLI) tool designed for seamless interaction with OpenAI\nmodels directly from your terminal. Effortlessly run queries, generate shell commands or code, create images from text,\nand more, using simple commands. Streamline your workflow and enhance productivity with this powerful and user-friendly\nCLI tool.\n\nDeveloped with the help of [SGPT](https://github.com/tbckr/sgpt).\n\nThis is a Go implementation. For the original Python implementation,\nvisit [shell-gpt](https://github.com/TheR1D/shell_gpt). Please keep this in mind when reporting issues.\n\n\u003e [!NOTE]\n\u003e Currently under heavy refactoring for v3, but v2 is still maintained.\n\n\u003c!-- START doctoc generated TOC please keep comment here to allow auto update --\u003e\n\u003c!-- DON'T EDIT THIS SECTION, INSTEAD RE-RUN doctoc TO UPDATE --\u003e\n\u003c!-- param::isNotitle::true:: --\u003e\n\n- [Features](#features)\n- [Installation](#installation)\n  - [Linux](#linux)\n  - [macOS](#macos)\n  - [Windows](#windows)\n  - [Using Go](#using-go)\n  - [Docker](#docker)\n  - [Ansible](#ansible)\n  - [Other platforms](#other-platforms)\n- [Usage Guide](#usage-guide)\n  - [Getting started: Obtaining an OpenAI API Key](#getting-started-obtaining-an-openai-api-key)\n  - [Querying OpenAI Models](#querying-openai-models)\n  - [GPT-4o and GPT-4 Vision API Support](#gpt-4o-and-gpt-4-vision-api-support)\n  - [o1 API Support](#o1-api-support)\n  - [OpenRouter API Support](#openrouter-api-support)\n  - [Chat Capabilities](#chat-capabilities)\n  - [Generating and Executing Shell Commands](#generating-and-executing-shell-commands)\n  - [Interactive Shell Sessions](#interactive-shell-sessions)\n  - [Code Generation Capabilities](#code-generation-capabilities)\n  - [Prompt Templating](#prompt-templating)\n  - [Enhancing Your Workflow with Bash Aliases and Functions](#enhancing-your-workflow-with-bash-aliases-and-functions)\n- [Acknowledgements](#acknowledgements)\n\n\u003c!-- END doctoc generated TOC please keep comment here to allow auto update --\u003e\n\n## Features\n\n- **Instant Answers:** Obtain quick and accurate responses to simple questions directly in your shell, streamlining your\n  workflow.\n- **GPT-4o Integration:** Access the capabilities of the [GPT-4o API](https://platform.openai.com/docs/models/gpt-4o)\n  to generate detailed and informative responses.\n- **GPT-4 Vision API:** Leverage the capabilities of\n  the [GPT-4 Vision API](https://platform.openai.com/docs/guides/vision) to analyze and generate insights from images.\n- **Shell Commands Generation:** Effortlessly generate and execute shell commands, simplifying complex tasks and\n  enhancing\n  productivity.\n- **Code Production:** Generate code snippets in various programming languages, making it easier to learn new languages\n  or\n  find solutions to coding problems.\n- **ChatGPT Integration:** Utilize ChatGPT's interactive chat capabilities to refine your prompts and achieve more\n  precise\n  results, benefiting from the powerful language model.\n- **Bash Functions and Aliases:** Seamlessly integrate SGPT responses into custom bash functions and aliases, optimizing\n  your workflows and making your daily tasks more efficient.\n- **OpenRouter Support:** Use [OpenRouter](https://openrouter.ai) to access various large language models (LLMs) via a\n  single API, providing flexibility and convenience in your interactions with different models.\n- **Prompt Templating:** Inject structured data into prompts using Go `text/template` syntax. Pipe YAML or JSON\n  variables via stdin to build dynamic, reusable prompt patterns.\n\nBy offering these versatile features, SGPT serves as a powerful tool to enhance your overall productivity, streamline\nyour workflow, and simplify complex tasks.\n\n## Installation\n\n### Linux\n\nSGPT has been tested on Ubuntu LTS releases and is expected to be compatible with the following Linux\ndistributions:\n\n- Debian\n- Ubuntu\n- Arch Linux\n- Fedora\n\nTo install, download the latest release from the [release page](https://github.com/tbckr/sgpt/releases) and use the\npackage manager specific to your distribution.\n\n### macOS\n\nFor users with Homebrew as their package manager, run the following command in the terminal:\n\n```shell\nbrew install tbckr/tap/sgpt\n```\n\n### Windows\n\nFor users with Scoop as their package manager, execute these commands in PowerShell:\n\n```shell\nscoop bucket add tbckr https://github.com/tbckr/scoop-bucket.git\nscoop install tbckr/sgpt\n```\n\n### Using Go\n\nTo install SGPT with Go, based on the git tag, use this command:\n\n```shell\ngo install github.com/tbckr/sgpt/v2/cmd/sgpt@latest\n```\n\n### Docker\n\nTo run SGPT with Docker, use the following command to pull the latest image:\n\n```shell\ndocker pull ghcr.io/tbckr/sgpt:latest\n```\n\nExamples on how to use SGPT with Docker can be found [here](https://sgpt.readthedocs.io/en/latest/usage/docker/).\n\n### Ansible\n\nTo install SGPT with Ansible, you can use the following ansible playbook as your base and adapt accordingly:\n\n```yaml\n---\n- hosts: all\n  tasks:\n    - name: Get latest sgpt release\n      uri:\n        url: \"https://api.github.com/repos/tbckr/sgpt/releases/latest\"\n        return_content: yes\n      register: sgpt_release\n\n    - name: Set latest version of sgpt\n      set_fact:\n        sgpt_latest_version: \"{{ sgpt_release.json.tag_name }}\"\n\n    - name: Install sgpt for debian based, amd64 systems\n      ansible.builtin.apt:\n        deb: https://github.com/tbckr/sgpt/releases/download/{{ sgpt_latest_version }}/sgpt_{{ sgpt_latest_version[1:] }}_amd64.deb\n        allow_unauthenticated: true\n```\n\nThe playbook can be run with the following command:\n\n```shell\nansible-playbook -i \u003cinventory\u003e \u003cplaybook\u003e.yml\n```\n\nThe latest version of the playbook can be found [here](https://github.com/tbckr/sgpt/blob/main/playbook.yml).\n\n### Other platforms\n\nFor other platforms, visit the GitHub [release page](https://github.com/tbckr/sgpt/releases) and download the latest\nrelease suitable for your system.\n\n## Usage Guide\n\nSee the [documentation](https://sgpt.readthedocs.io/en/stable/) for detailed usage instructions.\n\n### Getting started: Obtaining an OpenAI API Key\n\nTo use the OpenAI API, you must first obtain an API key.\n\n1. Visit [https://platform.openai.com/overview](https://platform.openai.com/overview) and sign up for an account.\n2. Navigate to [https://platform.openai.com/account/api-keys](https://platform.openai.com/account/api-keys) and generate\n   a new API key.\n3. On Linux or macOS: Update your `.bashrc` or `.zshrc` file to include the following export statement adding your API\n   key as the value:\n\n  ```shell\n  export OPENAI_API_KEY=\"sk-...\"\n  ```\n\n1. On Windows: [Update your environment variables](https://geekflare.com/system-environment-variables-in-windows/) to\n   include the `OPENAI_API_KEY` variable with your API key as the value.\n\nAfter completing these steps, you'll have an OpenAI API key that can be used to interact with the OpenAI models through\nthe SGPT tool.\n\n\u003e [!IMPORTANT]\n\u003e Your API key is sensitive information. Do not share it with anyone.\n\n### Querying OpenAI Models\n\nSGPT allows you to ask simple questions and receive informative answers. For example:\n\n```shell\n$ sgpt \"mass of sun\"\nThe mass of the sun is approximately 1.989 x 10^30 kilograms.\n```\n\nYou can also pass prompts to SGPT using pipes:\n\n```shell\n$ echo -n \"mass of sun\" | sgpt\nThe mass of the sun is approximately 1.989 x 10^30 kilograms.\n```\n\nYou can also add another prompt to the piped data by specifying the `stdin` modifier and then specifying the prompt:\n\n```shell\n$ echo \"Say: Hello World!\" | sgpt stdin 'Replace every \"World\" word with \"ChatGPT\"'\nHello ChatGPT!\n```\n\nIf you want to stream the completion to the command line, you can add the `--stream` flag. This will stream the output\nto the command line as it is generated.\n\n### GPT-4o and GPT-4 Vision API Support\n\nSGPT additionally facilitates the utilization of the GPT-4o and GPT-4 Vision API. Include input images using the `-i`\nor `--input` flag, supporting both URLs and local images.\n\n```shell\n$ sgpt -m \"gpt-4o\" -i pkg/fs/testdata/marvin.jpg \"what can you see on the picture?\"\nThe picture shows a robot with a large, round head and an expressive, downward-slanting triangular eye. The body of the robot is designed with a sleek, somewhat shiny, metallic structure and it is pointing with its right hand. The design appears to be humanoid with distinct arms, legs, and a segmented torso.\n$ sgpt -m \"gpt-4-vision-preview\" -i \"https://upload.wikimedia.org/wikipedia/en/c/cb/Marvin_%28HHGG%29.jpg\" \"what can you see on the picture?\"\nThe image shows a figure resembling a robot with a humanoid form. It has a\n```\n\nIt is also possible to combine URLs and local images:\n\n```shell\n$ sgpt -m \"gpt-4o\" -i \"https://upload.wikimedia.org/wikipedia/en/c/cb/Marvin_%28HHGG%29.jpg\" -i pkg/fs/testdata/marvin.jpg \"what is the difference between those two pictures\"\nThe two pictures you provided appear to be identical. There are no visible differences between them. Both show the same character in the same pose with the same lighting and background.\n```\n\nYou can also set the default model to GPT-4o or GPT-4 Vision by setting it in\nthe [configuration file](https://sgpt.readthedocs.io/en/stable/configuration/).\n\n**Important:** The GPT-4o and GPT-4-vision API integration is currently in beta and may change in the future.\n\n### o1 API Support\n\nIf you are already whitelisted for the o1 API, you can use it by specifying the model with the `-m` flag. You must also\nprovide the `--stream=false` flag to not stream the output as it is not supported by the o1 API (this is only necessary,\nif you have provided the stream option via the config file).\n\nExample:\n\n```shell\n$ sgpt -m \"o1-preview\" --stream=false \"how many rs are in strawberry?\"\nThere are three \"r\"s in the word \"strawberry\".\n```\n\nYou can also create a bash alias to use the o1 API more easily. For example, add the following line to your `.bashrc`:\n\n```shell\nalias sgpt-o1=\"sgpt -m \\\"o1-preview\\\" --stream=false\"\n```\n\nThen you can use the alias like this:\n\n```shell\n$ sgpt-o1 \"how many rs are in strawberry?\"\nThere are three \"r\"s in the word \"strawberry\".\n```\n\n**Important:** The o1 API does not support personas.\n\n### OpenRouter API Support\n\nSGPT seamlessly integrates with the [OpenRouter API](https://openrouter.ai), giving you access to a wide range of AI\nmodels beyond OpenAI's offerings.\n\n1. Set the OpenRouter API base URL environment variable:\n   ```shell\n   export OPENAI_API_BASE=\"https://openrouter.ai/api/v1\"\n   ```\n\n2. Create an API key at [OpenRouter](https://openrouter.ai/settings/keys) and set it as your environment variable:\n   ```shell\n   export OPENAI_API_KEY=\"your_openrouter_api_key\"\n   ```\n\nOnce configured, you can specify any OpenRouter-supported model with the `-m` flag:\n\n```shell\n$ sgpt -m \"anthropic/claude-3.7-sonnet\" \"mass of sun\"\nThe mass of the Sun is approximately:\n\n1.989 × 10^30 kilograms (kg)\n\nThis is roughly 333,000 times the mass of Earth. The Sun contains about 99.86% of all the mass in our solar system.\n```\n\nBrowse the complete list of available models on the [OpenRouter models page](https://openrouter.ai/models).\n\n\u003e [!TIP]\n\u003e Under [Integrations](https://openrouter.ai/settings/integrations) in your OpenRouter account, you can link your\n\u003e existing OpenAI API key. This allows you to use any remaining OpenAI credits when accessing OpenAI models through\n\u003e OpenRouter.\n\n### Chat Capabilities\n\nSGPT provides chat functionality that enables interactive conversations with OpenAI models. You can use the `--chat`\nflag to initiate and reference chat sessions.\n\nThe chat capabilities allow you to interact with OpenAI models in a more dynamic and engaging way, making it\neasier to obtain relevant responses, code, or shell commands through continuous conversations.\n\nThe example below demonstrates how to fine-tune the model's responses for more targeted outcomes.\n\n1. The first command initiates a chat session named `ls-files` and asks the model to \"list all files directory\":\n\n  ```shell\n  $ sgpt sh --chat ls-files \"list all files directory\"\n  ls\n  ```\n\n1. The second command continues the conversation within the `ls-files` chat session and requests to \"sort by name\":\n\n  ```shell\n  $ sgpt sh --chat ls-files \"sort by name\"\n  ls | sort\n  ```\n\nThe model provides the appropriate shell command `ls | sort`, which lists all files in a directory and sorts them by\nname.\n\n### Generating and Executing Shell Commands\n\nSGPT can generate shell commands based on your input:\n\n```shell\n$ sgpt sh \"make all files in current directory read only\"\nchmod -R 444 *\n```\n\nYou can also generate a shell command and execute it directly:\n\n```shell\n$ sgpt sh --execute \"make all files in current directory read only\"\nchmod -R 444 *\nDo you want to execute this command? (Y/n) y\n```\n\nThe `sh` command is a default persona to generate shell commands. For more information on personas, see\nthe [docs](https://sgpt.readthedocs.io/en/latest/usage/personas/).\n\n### Interactive Shell Sessions\n\nCurrently, SGPT does not support interactive shell sessions. However, `rlwrap` can be used to enable\ninteractive-like shell sessions ([source](https://github.com/tbckr/sgpt/issues/111#issuecomment-1869814041)):\n\n```text\n$ rlwrap bash -c 'echo ▶; while read in; do [[ -n \"$in\" ]] \u0026\u0026 echo ■ \u0026\u0026 sgpt --chat chat_name \"$in\" \u0026\u0026 echo ▶; done'\n▶\nmass of sun\n■\nThe mass of the Sun is approximately 1.989 x 10^30 kilograms, or about 330,000 times the mass of Earth. It contains about 99.86% of the total mass of the Solar System and is by far the most dominant object in it. The Sun's mass is composed mostly of hydrogen (~74%) and helium (~24%), with the remaining 2% consisting of heavier elements.\n▶\nconvert to earth masses\n■\nTo convert the mass of the Sun to Earth masses, you can simply divide the Sun's mass by the mass of the Earth. Given that:\n\n\nA. The Sun's mass is approximately 1.989 x 10^30 kilograms.\n\nB. The Earth's mass is approximately 5.972 x 10^24 kilograms.\n\nUsing these values, you can calculate how many Earth masses the Sun is:\n\n(1.989 x 10^30 kg) / (5.972 x 10^24 kg/Earth) = approximately 333,000 Earth masses\n\nSo the Sun is about 333,000 times more massive than the Earth.\n▶\n```\n\nA script with automated session name generation and notification support could look like this:\n\n```shell\n#!/usr/bin/env bash\n\nshopt -s -o errexit\nshopt -s -o pipefail\nshopt -s -o nounset\nshopt -s inherit_errexit\n\nexport CHAT=\"$(date '+%Y%m%d%H%M%S%3N')_$(tr -dc 'A-Za-z' \u003c/dev/urandom | head -c 3)\"\nrlwrap bash -c 'echo ▶; while read in; do [[ -n \"$in\" ]] \u0026\u0026 echo ■ \u0026\u0026 sgpt --chat \"$CHAT\" \"$in\" \u0026\u0026 echo ▶ \u0026\u0026 notify-send --urgency=low 💬 ; done'\n```\n\nThanks to @ilya-bystrov for coming up with this solution.\n\n### Code Generation Capabilities\n\nSGPT can efficiently generate code based on given instructions. For instance, to solve the classic FizzBuzz problem\nusing Python, simply provide the prompt as follows:\n\n```shell\n$ sgpt code \"Solve classic fizz buzz problem using Python\"\nfor i in range(1, 101):\n    if i % 3 == 0 and i % 5 == 0:\n        print(\"FizzBuzz\")\n    elif i % 3 == 0:\n        print(\"Fizz\")\n    elif i % 5 == 0:\n        print(\"Buzz\")\n    else:\n        print(i)\n```\n\nSGPT will return the appropriate Python code to address the FizzBuzz problem.\n\nThe `code` command is a default persona to generate code. For more information on personas, see\nthe [docs](https://sgpt.readthedocs.io/en/latest/usage/personas/).\n\n### Prompt Templating\n\nThe `--template` flag (`-T`) lets you pipe YAML or JSON data as variables into a Go template string:\n\n```shell\n$ echo \"name: Dave\\ncountry: France\" | sgpt --template \"What would {{ .name }} be called in {{ .country }}?\"\n\n$ echo \"lang: Python\" | sgpt code --template \"Write a hello world program in {{ .lang }}\"\n```\n\nSee the [full documentation](https://sgpt.readthedocs.io/en/latest/usage/templates/) for all options and constraints.\n\n### Enhancing Your Workflow with Bash Aliases and Functions\n\nSGPT can be further integrated into your workflow by creating bash aliases and functions. This enables you to automate\ncommon tasks and improve efficiency when working with OpenAI models and shell commands.\n\nIndeed, you can configure SGPT to generate your git commit message using the following bash function:\n\n```shell\ngsum() {\n  commit_message=\"$(sgpt txt \"Generate git commit message, my changes: $(git diff)\")\"\n  printf \"%s\\n\" \"$commit_message\"\n  read -rp \"Do you want to commit your changes with this commit message? [y/N] \" response\n  if [[ $response =~ ^[Yy]$ ]]; then\n    git add . \u0026\u0026 git commit -m \"$commit_message\"\n  else\n    echo \"Commit cancelled.\"\n  fi\n}\n```\n\nFor instance, the commit message for this description and bash function would appear as follows:\n\n```shell\n$ gsum\nfeat: Add bash function to generate git commit messages\n\nAdded `gsum()` function to `.bash_aliases` that generates a commit message using sgpt to summarize git changes.\nThe user is prompted to confirm the commit message before executing `git add . \u0026\u0026 git commit -m \"\u003ccommit_message\u003e\"`.\nThis function is meant to automate the commit process and increase productivity in daily work.\n\nAdditionally, updated the README.md file to include information about the new bash function and added a section to\nshowcase useful bash aliases and functions found in `.bash_aliases`.\nDo you want to commit your changes with this commit message? [y/N] y\n[main d6db80a] feat: Add bash function to generate git commit messages\n 2 files changed, 48 insertions(+)\n create mode 100644 .bash_aliases\n```\n\nA compilation of beneficial bash aliases and functions, including an updated gsum function, is available\nin [.bashrc](.bashrc).\n\n## Acknowledgements\n\nInspired by [shell-gpt](https://github.com/TheR1D/shell_gpt).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftbckr%2Fsgpt","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftbckr%2Fsgpt","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftbckr%2Fsgpt/lists"}