{"id":15064331,"url":"https://github.com/belingud/gptcomet","last_synced_at":"2026-01-26T11:16:12.297Z","repository":{"id":252504847,"uuid":"837247857","full_name":"belingud/gptcomet","owner":"belingud","description":"GPTComet: AI-Powered Git Commit Message Generator","archived":false,"fork":false,"pushed_at":"2026-01-18T14:14:54.000Z","size":1955,"stargazers_count":17,"open_issues_count":0,"forks_count":3,"subscribers_count":1,"default_branch":"master","last_synced_at":"2026-01-18T22:14:05.380Z","etag":null,"topics":["ai","chatgpt","cli","commit","commit-message","git","gpt"],"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/belingud.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":"CONTRIBUTING.rst","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":"AGENTS.md","dco":null,"cla":null}},"created_at":"2024-08-02T14:24:37.000Z","updated_at":"2026-01-18T14:14:54.000Z","dependencies_parsed_at":"2024-11-10T13:31:57.538Z","dependency_job_id":"2d9c339e-81ff-409e-815a-369c9918fbb3","html_url":"https://github.com/belingud/gptcomet","commit_stats":{"total_commits":88,"total_committers":1,"mean_commits":88.0,"dds":0.0,"last_synced_commit":"72365efecc9a9b714e1a501de6fd0f4f68a1e46a"},"previous_names":["belingud/aicommit","belingud/gptcommits"],"tags_count":68,"template":false,"template_full_name":null,"purl":"pkg:github/belingud/gptcomet","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/belingud%2Fgptcomet","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/belingud%2Fgptcomet/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/belingud%2Fgptcomet/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/belingud%2Fgptcomet/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/belingud","download_url":"https://codeload.github.com/belingud/gptcomet/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/belingud%2Fgptcomet/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28776962,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-26T09:42:00.929Z","status":"ssl_error","status_checked_at":"2026-01-26T09:42:00.591Z","response_time":59,"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":["ai","chatgpt","cli","commit","commit-message","git","gpt"],"created_at":"2024-09-25T00:15:25.836Z","updated_at":"2026-01-26T11:16:12.239Z","avatar_url":"https://github.com/belingud.png","language":"Go","funding_links":[],"categories":["Terminal","Tools \u0026 Resources","Go"],"sub_categories":["CLI Utilities"],"readme":"# GPTComet: AI-Powered Git Commit Message Generator And Reviewer\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"artwork/logo.png\" width=\"150\" height=\"150\" alt=\"GPTComet Logo\"\u003e\n\u003c/p\u003e\n\n\u003ca href=\"https://www.producthunt.com/posts/gptcomet?embed=true\u0026utm_source=badge-featured\u0026utm_medium=badge\u0026utm_source=badge-gptcomet\" target=\"_blank\"\u003e\u003cimg src=\"https://api.producthunt.com/widgets/embed-image/v1/featured.svg?post_id=774818\u0026theme=neutral\u0026t=1747386848397\" alt=\"GPTComet - GPTComet\u0026#0058;\u0026#0032;AI\u0026#0045;Powered\u0026#0032;Git\u0026#0032;Commit\u0026#0032;Message\u0026#0032;Generator | Product Hunt\" style=\"width: 250px; height: 54px;\" width=\"250\" height=\"54\" /\u003e\u003c/a\u003e\n\n[![PyPI version](https://img.shields.io/pypi/v/gptcomet?style=for-the-badge)](https://pypi.org/project/gptcomet/)\n![GitHub Release](https://img.shields.io/github/v/release/belingud/gptcomet?style=for-the-badge)\n[![License](https://img.shields.io/github/license/belingud/gptcomet.svg?style=for-the-badge)](https://opensource.org/licenses/MIT)\n![GitHub go.mod Go version](https://img.shields.io/github/go-mod/go-version/belingud/gptcomet?style=for-the-badge)\n![GitHub Actions Workflow Status](https://img.shields.io/github/actions/workflow/status/belingud/gptcomet/release.yml?style=for-the-badge)\n![PyPI - Downloads](https://img.shields.io/pypi/dm/gptcomet?logo=pypi\u0026style=for-the-badge)\n![Pepy Total Downloads](https://img.shields.io/pepy/dt/gptcomet?style=for-the-badge\u0026logo=python)\n![GitHub Downloads (all assets, all releases)](https://img.shields.io/github/downloads/belingud/gptcomet/total?style=for-the-badge\u0026label=Release%20Download)\n\n\u003c!-- TOC --\u003e\n\n- [GPTComet: AI-Powered Git Commit Message Generator And Reviewer](#gptcomet-ai-powered-git-commit-message-generator-and-reviewer)\n  - [💡 Overview](#-overview)\n  - [✨ Features](#-features)\n  - [⬇️ Installation](#️-installation)\n  - [📕 Usage](#-usage)\n  - [🔧 Setup](#-setup)\n    - [Configuration Methods](#configuration-methods)\n    - [Provider Setup Guide](#provider-setup-guide)\n      - [OpenAI](#openai)\n      - [Gemini](#gemini)\n      - [Claude/Anthropic](#claudeanthropic)\n      - [Vertex](#vertex)\n      - [Azure](#azure)\n      - [Ollama](#ollama)\n      - [Other Supported Providers](#other-supported-providers)\n    - [Manual Provider Setup](#manual-provider-setup)\n  - [⌨️ Commands](#️-commands)\n  - [⚙ Configuration](#-configuration)\n    - [file\\_ignore](#file_ignore)\n    - [provider](#provider)\n    - [output](#output)\n    - [Markdown theme](#markdown-theme)\n    - [Supported languages](#supported-languages)\n    - [console](#console)\n  - [🔦 Supported Keys](#-supported-keys)\n  - [📃 Example](#-example)\n    - [Basic Usage](#basic-usage)\n    - [Enhanced Error Messages](#enhanced-error-messages)\n    - [Progress Indicators](#progress-indicators)\n  - [💻 Development](#-development)\n    - [Requirements](#requirements)\n    - [Setup](#setup)\n    - [Running Tests](#running-tests)\n      - [Go Tests](#go-tests)\n      - [Python Tests](#python-tests)\n    - [Code Quality](#code-quality)\n      - [Go](#go)\n      - [Python](#python)\n    - [Build](#build)\n  - [📩 Contact](#-contact)\n  - [☕️ Sponsor](#️-sponsor)\n  - [📜 License](#-license)\n\n\u003c!-- /TOC --\u003e\n\n## 💡 Overview\n\nGPTComet is an AI-powered developer tool that streamlines your Git workflow and enhances code quality through automated commit message generation and intelligent code review.\n\n## ✨ Features\n\nThis project leverages the power of large language models to automate repetitive tasks and improve the overall development process. The core features include:\n\n-   **Automatic Commit Message Generation**: GPTComet can generate commit messages based on the changes made in the code.\n-   **Intelligent Code Review**: Get AI-powered code reviews with actionable feedback and suggestions.\n-   **Progress Indicators**: Optional verbose mode shows real-time progress for long-running operations.\n-   **Support for Multiple Languages**: GPTComet supports multiple languages, including English, Chinese and so on.\n-   **Customizable Configuration**: GPTComet allows users to customize the configuration to suit their needs, such llm model and prompt.\n-   **Support for Rich Commit Messages**: GPTComet supports rich commit messages, which include a title, summary, and detailed description.\n-   **Support for Multiple Providers**: GPTComet supports multiple providers, including OpenAI, Gemini, Claude/Anthropic, Vertex, Azure, Ollama, and others.\n-   **Support SVN and Git**: GPTComet supports both SVN and Git repositories.\n\n## ⬇️ Installation\n\nTo use GPTComet, you can download from [Github release](https://github.com/belingud/gptcomet/releases/latest), or by install scripts:\n\n```bash\ncurl -sSL https://cdn.jsdelivr.net/gh/belingud/gptcomet@master/install.sh | bash\n```\n\n\nWindows:\n\n```powershell\nirm https://cdn.jsdelivr.net/gh/belingud/gptcomet@master/install.ps1 | iex\n```\nIf you want to install specific version, you can use the following script:\n\n```bash\ncurl -sSL https://cdn.jsdelivr.net/gh/belingud/gptcomet@master/install.sh | bash -s -- -v 0.4.2\n```\n\n```powershell\nirm https://cdn.jsdelivr.net/gh/belingud/gptcomet@master/install.ps1 | iex -CommandArgs @(\"-v\", \"0.4.2\")\n```\n\nIf you prefer to run in python, you can install by `pip` directly, it packaged the binary files corresponding to the platform already.\n\n```shell\npip install gptcomet\n\n# Using pipx\npipx install gptcomet\n\n# Using uv\nuv tool install gptcomet\nResolved 1 package in 1.33s\nInstalled 1 package in 8ms\n + gptcomet==0.1.6\nInstalled 2 executables: gmsg, gptcomet\n```\n\n## 📕 Usage\n\nTo use gptcomet, follow these steps:\n\n1.  **Install GPTComet**: Install GPTComet through pypi.\n2.  **Configure GPTComet**: See [Setup](#setup). Configure GPTComet with your api_key and other required keys like:\n\n-   `provider`: The provider of the language model (default `openai`).\n-   `api_base`: The base URL of the API (default `https://api.openai.com/v1`).\n-   `api_key`: The API key for the provider.\n-   `model`: The model used for generating commit messages (default `gpt-4o`).\n\n3.  **Run GPTComet**: Run GPTComet using the following command: `gmsg commit`.\n\nIf you are using `openai` provider, and finished set `api_key`, you can run `gmsg commit` directly.\n\n## 🔧 Setup\n\n### Configuration Methods\n\n1. **Direct Configuration**\n\n    - Configure directly in `~/.config/gptcomet/gptcomet.yaml`.\n\n2. **Interactive Setup**\n    - Use the `gmsg newprovider` command for guided setup.\n\n### Provider Setup Guide\n\n![Made with VHS](https://vhs.charm.sh/vhs-6019QMIveifvh9vGKc2ZZ8.gif)\n\n```bash\ngmsg newprovider\n\n    Select Provider\n\n  \u003e 1. azure\n    2. chatglm\n    3. claude\n    4. cohere\n    5. deepseek\n    6. gemini\n    7. groq\n    8. kimi\n    9. mistral\n    10. ollama\n    11. openai\n    12. openrouter\n    13. sambanova\n    14. silicon\n    15. tongyi\n    16. vertex\n    17. xai\n    18. Input Manually\n\n    ↑/k up • ↓/j down • ? more\n```\n\n#### OpenAI\n\nOpenAI api key page: https://platform.openai.com/api-keys\n\n```shell\ngmsg newprovider\n\nSelected provider: openai\nConfigure provider:\n\nPrevious inputs:\n  Enter OpenAI API base: https://api.openai.com/v1\n  Enter API key: sk-abc*********************************************\n  Enter max tokens: 1024\n\nEnter Enter model name (default: gpt-4o):\n\u003e gpt-4o\n\n\nProvider openai configured successfully!\n```\n\n#### Gemini\n\nGemini api key page: https://aistudio.google.com/u/1/apikey\n\n```shell\ngmsg newprovider\nSelected provider: gemini\nConfigure provider:\n\nPrevious inputs:\n  Enter Gemini API base: https://generativelanguage.googleapis.com/v1beta/models\n  Enter API key: AIz************************************\n  Enter max tokens: 1024\n\nEnter Enter model name (default: gemini-1.5-flash):\n\u003e gemini-2.0-flash-exp\n\nProvider gemini already has a configuration. Do you want to overwrite it? (y/N): y\n\nProvider gemini configured successfully!\n```\n\n#### Claude/Anthropic\n\nI don't have an anthropic account yet, please see [Anthropic console](https://console.anthropic.com)\n\n#### Vertex\n\nVertex console page: https://console.cloud.google.com\n\n```shell\ngmsg newprovider\nSelected provider: vertex\nConfigure provider:\n\nPrevious inputs:\n  Enter Vertex AI API Base URL: https://us-central1-aiplatform.googleapis.com/v1\n  Enter API key: sk-awz*********************************************\n  Enter location (e.g., us-central1): us-central1\n  Enter max tokens: 1024\n  Enter model name: gemini-1.5-pro\n\nEnter Enter Google Cloud project ID:\n\u003e test-project\n\n\nProvider vertex configured successfully!\n```\n\n#### Azure\n\n```shell\ngmsg newprovider\n\nSelected provider: azure\nConfigure provider:\n\nPrevious inputs:\n  Enter Azure OpenAI endpoint: https://gptcomet.openai.azure.com\n  Enter API key: ********************************\n  Enter API version: 2024-02-15-preview\n  Enter Azure OpenAI deployment name: gpt4o\n  Enter max tokens: 1024\n\nEnter Enter deployment name (default: gpt-4o):\n\u003e gpt-4o\n\n\nProvider azure configured successfully!\n```\n\n#### Ollama\n\n```shell\ngmsg newprovider\nSelected provider: ollama\nConfigure provider:\n\nPrevious inputs:\n  Enter Ollama API Base URL: http://localhost:11434/api\n  Enter max tokens: 1024\n\nEnter Enter model name (default: llama2):\n\u003e llama2\n\n\nProvider ollama configured successfully!\n```\n\n#### Other Supported Providers\n\n-   Groq\n-   Mistral\n-   Tongyi/Qwen\n-   XAI\n-   Sambanova\n-   Silicon\n-   Deepseek\n-   ChatGLM\n-   KIMI\n-   Cohere\n-   OpenRouter\n-   Hunyuan\n-   ModelScope\n-   MiniMax\n-   Yi (lingyiwanwu)\n\nNot supported:\n\n-   Baidu ERNIE\n\n### Manual Provider Setup\n\nOr you can enter the provider name manually, and setup config manually.\n\n```shell\ngmsg newprovider\nYou can either select one from the list or enter a custom provider name.\n  ...\n  vertex\n\u003e Input manually\n\nEnter provider name: test\nEnter OpenAI API Base URL [https://api.openai.com/v1]:\nEnter model name [gpt-4o]:\nEnter API key: ************************************\nEnter max tokens [1024]:\n[GPTComet] Provider test configured successfully.\n```\n\nSome special provider may need your custome config. Like `cloudflare`.\n\n\u003e Be aware that the model name is not used in cloudflare api.\n\n```shell\n$ gmsg newprovider\n\nSelected provider: cloudflare\nConfigure provider:\n\nPrevious inputs:\n  Enter API Base URL: https://api.cloudflare.com/client/v4/accounts/\u003caccount_id\u003e/ai/run\n  Enter model name: llama-3.3-70b-instruct-fp8-fast\n  Enter API key: abc*************************************\n\nEnter Enter max tokens (default: 1024):\n\u003e 1024\n\nProvider cloudflare already has a configuration. Do you want to overwrite it? (y/N): y\n\nProvider cloudflare configured successfully!\n\n$ gmsg config set cloudflare.completion_path @cf/meta/llama-3.3-70b-instruct-fp8-fast\n$ gmsg config set cloudflare.answer_path result.response\n```\n\n## ⌨️ Commands\n\nThe following are the available commands for GPTComet:\n\n-   `gmsg config`: Config manage commands group.\n    -   `get \u003ckey\u003e`: Get the value of a configuration key.\n    -   `list`: List the entire configuration content.\n    -   `reset`: Reset the configuration to default values (optionally reset only the prompt section with `--prompt`).\n    -   `set \u003ckey\u003e \u003cvalue\u003e`: Set a configuration value.\n    -   `path`: Get the configuration file path.\n    -   `remove \u003ckey\u003e [value]`: Remove a configuration key or a value from a list. (List value only, like `fileignore`)\n    -   `append \u003ckey\u003e \u003cvalue\u003e`: Append a value to a list configuration.(List value only, like `fileignore`)\n    -   `keys`: List all supported configuration keys.\n-   `gmsg commit`: Generate commit message by changes/diff.\n    -   `--svn`: Generate commit message for svn.\n    -   `--dry-run`: Dry run the command without actually generating the commit message.\n    -   `-y/--yes`: Skip the confirmation prompt.\n    -   `--no-verify`: Skip git hooks verification, akin to using `git commit --no-verify`\n    -   `--repo`: Path to the repository (default \".\").\n    -   `--answer-path`: Override answer path\n    -   `--api-base`: Override API base URL\n    -   `--api-key`: Override API key\n    -   `--completion-path`: Override completion path\n    -   `--frequency-penalty`: Override frequency penalty\n    -   `--max-tokens`: Override maximum tokens\n    -   `--model`: Override model name\n    -   `--provider`: Override AI provider (openai/deepseek)\n    -   `--proxy`: Override proxy URL\n    -   `--retries`: Override retry count\n    -   `--temperature`: Override temperature\n    -   `--top-p`: Override top_p value\n-   `gmsg newprovider`: Add a new provider.\n-   `gmsg review`: Review staged diff or pipe to `gmsg review`.\n    -   `--svn`: Get diff from svn.\n    -   `--stream`: Stream output as it arrives from the LLM.\n    -   `--repo`: Path to the repository (default \".\").\n    -   `--answer-path`: Override answer path\n    -   `--api-base`: Override API base URL\n    -   `--api-key`: Override API key\n    -   `--completion-path`: Override completion path\n    -   `--frequency-penalty`: Override frequency penalty\n    -   `--max-tokens`: Override maximum tokens\n    -   `--model`: Override model name\n    -   `--provider`: Override AI provider (openai/deepseek)\n    -   `--proxy`: Override proxy URL\n    -   `--retries`: Override retry count\n    -   `--temperature`: Override temperature\n    -   `--top-p`: Override top_p value\n\nGlobal flags:\n\n```shell\n  -c, --config string   Config file path\n  -d, --debug           Enable debug mode\n```\n\n## ⚙ Configuration\n\nHere's a summary of the main configuration keys:\n\n| Key                            | Description                                                | Default Value                     |\n| :----------------------------- | :--------------------------------------------------------- | :-------------------------------- |\n| `provider`                     | The name of the LLM provider to use.                       | `openai`                          |\n| `file_ignore`                  | A list of file patterns to ignore in the diff.             | (See [file_ignore](#file_ignore)) |\n| `output.lang`                  | The language for commit message generation.                | `en`                              |\n| `output.rich_template`         | The template to use for rich commit messages.              | `\u003ctitle\u003e:\u003csummary\u003e\\n\\n\u003cdetail\u003e`   |\n| `output.translate_title`       | Translate the title of the commit message.                 | `false`                           |\n| `output.review_lang`           | The language to generate the review message.               | `en`                              |\n| `output.markdown_theme`        | The theme to display markdown_theme content.               | `auto`                            |\n| `console.verbose`              | Enable verbose output with progress indicators and detailed error messages. | `true`                            |\n| `\u003cprovider\u003e.api_base`          | The API base URL for the provider.                         | (Provider-specific)               |\n| `\u003cprovider\u003e.api_key`           | The API key for the provider.                              |                                   |\n| `\u003cprovider\u003e.model`             | The model name to use.                                     | (Provider-specific)               |\n| `\u003cprovider\u003e.retries`           | The number of retry attempts for API requests.             | `2`                               |\n| `\u003cprovider\u003e.proxy`             | The proxy URL to use (if needed).                          |                                   |\n| `\u003cprovider\u003e.max_tokens`        | The maximum number of tokens to generate.                  | `2048`                            |\n| `\u003cprovider\u003e.top_p`             | The top-p value for nucleus sampling.                      | `0.7`                             |\n| `\u003cprovider\u003e.temperature`       | The temperature value for controlling randomness.          | `0.7`                             |\n| `\u003cprovider\u003e.frequency_penalty` | The frequency penalty value.                               | `0`                               |\n| `\u003cprovider\u003e.extra_headers`     | Extra headers to include in API requests (JSON string).    | `{}`                              |\n| `\u003cprovider\u003e.extra_body`        | Extra body to include in API requests (JSON string).       | `{}`                              |\n| `\u003cprovider\u003e.completion_path`   | The API path for completion requests.                      | (Provider-specific)               |\n| `\u003cprovider\u003e.answer_path`       | The JSON path to extract the answer from the API response. | (Provider-specific)               |\n| `prompt.brief_commit_message`  | The prompt template for generating brief commit messages.  | (See `defaults/defaults.go`)      |\n| `prompt.rich_commit_message`   | The prompt template for generating rich commit messages.   | (See `defaults/defaults.go`)      |\n| `prompt.translation`           | The prompt template for translating commit messages.       | (See `defaults/defaults.go`)      |\n\n**Note:** `\u003cprovider\u003e` should be replaced with the actual provider name (e.g., `openai`, `gemini`, `claude`).\n\nSome providers require specific keys, such as Vertex needing project ID, location, etc.\n\nThe configuration file for GPTComet is `gptcomet.yaml`. The file should contain the following keys:\n\n`output.translate_title` is used to determine whether to translate the title of the commit message.\n\nFor example in `output.lang: zh-cn`, the title of the commit message is `feat: Add new feature`\n\nIf `output.translate_title` is set to `true`, the commit message will be translated to `功能：新增功能`.\nOtherwise, the commit message will be translated to `feat: 新增功能`.\n\nIn some case you can set `complation_path` to empty string, like `\u003cprovider\u003e.completion_path: \"\"`, to use `api_base` endpoint directly.\n\n### file_ignore\n\nThe file to ignore when generating a commit. The default value is\n\n```yaml\n- bun.lockb\n- Cargo.lock\n- composer.lock\n- Gemfile.lock\n- package-lock.json\n- pnpm-lock.yaml\n- poetry.lock\n- yarn.lock\n- pdm.lock\n- Pipfile.lock\n- \"*.py[cod]\"\n- go.sum\n- uv.lock\n```\n\nYou can add more file_ignore by using the `gmsg config append file_ignore \u003cxxx\u003e` command.\n`\u003cxxx\u003e` is same syntax as `gitignore`, like `*.so` to ignore all `.so` suffix files.\n\n### provider\n\nThe provider configuration of the language model.\n\nThe default provider is `openai`.\n\nProvider config just like:\n\n```yaml\nprovider: openai\nopenai:\n    api_base: https://api.openai.com/v1\n    api_key: YOUR_API_KEY\n    model: gpt-4o\n    retries: 2\n    max_tokens: 1024\n    temperature: 0.7\n    top_p: 0.7\n    frequency_penalty: 0\n    extra_headers: {}\n    answer_path: choices.0.message.content\n    completion_path: /chat/completions\n```\n\nIf you are using `openai`, just leave the `api_base` as default. Set your `api_key` in the `config` section.\n\nIf you are using an `openai` class provider, or a provider compatible interface, you can set the provider to `openai`.\nAnd set your custom `api_base`, `api_key` and `model`.\n\nFor example:\n\n`Openrouter` providers api interface compatible with openai,\nyou can set provider to `openai` and set `api_base` to `https://openrouter.ai/api/v1`,\n`api_key` to your api key from [keys page](https://openrouter.ai/settings/keys)\nand `model` to `meta-llama/llama-3.1-8b-instruct:free` or some other you prefer.\n\n```shell\ngmsg config set openai.api_base https://openrouter.ai/api/v1\ngmsg config set openai.api_key YOUR_API_KEY\ngmsg config set openai.model meta-llama/llama-3.1-8b-instruct:free\ngmsg config set openai.max_tokens 1024\n```\n\nSilicon providers the similar interface with openrouter, so you can set provider to `openai`\nand set `api_base` to `https://api.siliconflow.cn/v1`.\n\n**Note that max tokens may vary, and will return an error if it is too large.**\n\n### output\n\nThe output configuration of the commit message.\n\nThe default output is\n\n```yaml\noutput:\n    lang: en\n    rich_template: \"\u003ctitle\u003e:\u003csummary\u003e\\n\\n\u003cdetail\u003e\"\n    translate_title: false\n    review_lang: \"en\"\n    markdown_theme: \"auto\"\n```\n\nYou can set `rich_template` to change the template of the rich commit message,\nand set `lang` to change the language of the commit message.\n\n### Markdown theme\n\nSupported markdown theme:\n\n-   `auto`: Auto detect markdown theme (default).\n-   `ascii`: ASCII style.\n-   `dark`: Dark theme.\n-   `dracula`: Dracula theme.\n-   `light`: Light theme.\n-   `tokyo-night`: Tokyo Night theme.\n-   `notty`: Notty style, no render.\n-   `pink`: Pink theme.\n\nIf you not set `markdown_theme`, the markdown theme will be auto detected.\nIf you are using light terminal, the markdown theme will be `dark`, if you are using dark terminal, the markdown theme will be `light`.\n\nGPTComet is using glamour to render markdown, you can preview the markdown theme in [glamour preview](https://github.com/charmbracelet/glamour/tree/master/styles/gallery#glamour-style-section).\n\n### Supported languages\n\n`output.lang` and `output.review_lang` support the following languages:\n\n-   `en`: English\n-   `zh-cn`: Simplified Chinese\n-   `zh-tw`: Traditional Chinese\n-   `fr`: French\n-   `vi`: Vietnamese\n-   `ja`: Japanese\n-   `ko`: Korean\n-   `ru`: Russian\n-   `tr`: Turkish\n-   `id`: Indonesian\n-   `th`: Thai\n-   `de`: German\n-   `es`: Spanish\n-   `pt`: Portuguese\n-   `it`: Italian\n-   `ar`: Arabic\n-   `hi`: Hindi\n-   `el`: Greek\n-   `pl`: Polish\n-   `nl`: Dutch\n-   `sv`: Swedish\n-   `fi`: Finnish\n-   `hu`: Hungarian\n-   `cs`: Czech\n-   `ro`: Romanian\n-   `bg`: Bulgarian\n-   `uk`: Ukrainian\n-   `he`: Hebrew\n-   `lt`: Lithuanian\n-   `la`: Latin\n-   `ca`: Catalan\n-   `sr`: Serbian\n-   `sl`: Slovenian\n-   `mk`: Macedonian\n-   `lv`: Latvian\n\n### console\n\nThe console output config.\n\nThe default console is\n\n```yaml\nconsole:\n    verbose: true\n```\n\nWhen `verbose` is enabled (`true`), GPTComet provides enhanced user experience:\n\n- **Progress Indicators**: Shows real-time progress for commit message generation and code review\n  ```\n  [1/2] Fetching git diff...\n  ✓ Fetching git diff (0.07s)\n  Discovered provider: mistral, model: codestral-latest\n  [2/2] Generating message...\n  ✓ Generating message (13.24s)\n  ```\n\n- **Detailed Operation Information**: Displays which provider and model are being used\n\n- **Enhanced Error Messages**: All errors include:\n  - Clear problem description\n  - Specific suggestions for resolution\n  - Relevant documentation links\n  - Appropriate emoji indicators for quick identification\n\nWhen `verbose` is disabled (`false`), GPTComet runs in silent mode with minimal output, suitable for scripting and automated workflows.\n\n## 🔦 Supported Keys\n\nYou can use `gmsg config keys` to check supported keys.\n\n## 📃 Example\n\nHere is an example of how to use GPTComet:\n\n### Basic Usage\n\n1.  When you first set your OpenAI KEY by `gmsg config set openai.api_key YOUR_API_KEY`, it will generate config file at `~/.local/gptcomet/gptcomet.yaml`, includes:\n\n```\nprovider: \"openai\"\nopenai:\n  api_base: \"https://api.openai.com/v1\"\n  api_key: \"YOUR_API_KEY\"\n  model: \"gpt-4o\"\n  retries: 2\noutput:\n  lang: \"en\"\n```\n\n2.  Run the following command to generate a commit message: `gmsg commit`\n3.  GPTComet will generate a commit message based on the changes made in the code and display it in the console.\n\n### Enhanced Error Messages\n\nGPTComet provides helpful error messages with actionable suggestions:\n\n```bash\n$ gmsg commit\n\n❌ API Key Not Configured\n\nProvider 'openai' requires an API key, but none was found.\n\nWhat to do:\n  • Set API key: gmsg config set openai.api_key \u003cyour-key\u003e\n  • Or set env var: export OPENAI_API_KEY=\u003cyour-key\u003e\n  • Check provider: gmsg config get openai\n\nDocs: https://github.com/belingud/gptcomet#configuration\n```\n\n### Progress Indicators\n\nWhen `console.verbose` is enabled (default), you'll see real-time progress:\n\n```bash\n$ gmsg commit\n\n[1/2] Fetching git diff...(0.07s)\nDiscovered provider: mistral, model: codestral-latest\n[2/2] Generating message...\n📤 Sending request to mistral...\nToken usage\u003e prompt: 1341, completion: 10, total: 1,351\n✓ Generating message (13.24s)\n\nfeat: add user authentication feature\n```\n\nTo disable progress indicators and run in silent mode:\n\n```bash\ngmsg config set console.verbose false\n```\n\nNote: Replace `YOUR_API_KEY` with your actual API key for the provider.\n\n## 💻 Development\n\n### Requirements\n- Go 1.25+\n- Python 3.9+\n- just command runner\n- pytest (for Python tests)\n\n### Setup\n\nIf you'd like to contribute to GPTComet, feel free to fork this project and submit a pull request.\n\nFirst, fork the project and clone your repo.\n\n```shell\ngit clone https://github.com/\u003cyourname\u003e/gptcomet\n```\n\nSecond, make sure you have `uv`, you can install by `pip`, `brew` or other way in their [installation](https://docs.astral.sh/uv/getting-started/installation/) docs\n\nUse `just` command to install dependencies:\n\n```shell\njust install\n```\n\n### Running Tests\n\n#### Go Tests\n\n```bash\n# Run all Go tests\ngo test ./...\n\n# Run specific package tests\ngo test ./internal/llm/\n\n# Run with coverage\ngo test -coverprofile=coverage.out ./...\ngo tool cover -html=coverage.out\n\n# Using just\njust test              # Run tests with coverage\njust test-coverage     # Generate coverage report\njust test-cover-func   # Show coverage by function\n```\n\n#### Python Tests\n\n```bash\n# Run Python wrapper tests\njust test-py\n\n# Run with coverage\njust test-py-cov\n\n# Or manually with uv\nuv run pytest tests/py_tests/ -v\nuv run pytest tests/py_tests/ --cov=py/gptcomet --cov-report=html\n```\n\n### Code Quality\n\n#### Go\n\n```bash\n# Static analysis\ngo vet ./...\nstaticcheck ./...\n\n# Using just\njust check             # Run go vet and staticcheck\njust format            # Format Go code\n```\n\n#### Python\n\n```bash\n# Code linting\nruff check py/\n\n# Formatting\nruff format py/\n```\n\n### Build\n\n```bash\n# Build Go binary\njust build\n\n# Build all platforms\njust build-all\n\n# Build Python wheel\njust build-py\n```\n\n## 📩 Contact\n\nIf you have any questions or suggestions, feel free to contact.\n\n## ☕️ Sponsor\n\nIf you like GPTComet, you can buy me a coffee to support me. Any support can help the project go further.\n\n[Buy Me A Coffee](./SPONSOR.md)\n\n## 📜 License\n\nGPTComet is licensed under the MIT License.\n\n[![FOSSA Status](https://app.fossa.com/api/projects/git%2Bgithub.com%2Fbelingud%2Fgptcomet.svg?type=large\u0026issueType=license)](https://app.fossa.com/projects/git%2Bgithub.com%2Fbelingud%2Fgptcomet?ref=badge_large\u0026issueType=license)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbelingud%2Fgptcomet","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbelingud%2Fgptcomet","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbelingud%2Fgptcomet/lists"}