{"id":13585068,"url":"https://github.com/chidiwilliams/GPT-Automator","last_synced_at":"2025-04-07T06:32:29.302Z","repository":{"id":105213283,"uuid":"600404645","full_name":"chidiwilliams/GPT-Automator","owner":"chidiwilliams","description":"Your voice-controlled Mac assistant","archived":false,"fork":false,"pushed_at":"2023-02-13T19:22:03.000Z","size":1622,"stargazers_count":229,"open_issues_count":0,"forks_count":31,"subscribers_count":7,"default_branch":"main","last_synced_at":"2024-10-26T19:32:46.609Z","etag":null,"topics":["automator","gpt-3","langchain","macos"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/chidiwilliams.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null}},"created_at":"2023-02-11T11:46:30.000Z","updated_at":"2024-10-23T22:52:39.000Z","dependencies_parsed_at":null,"dependency_job_id":"d67be288-c7b3-45a6-a2e8-eb887f871519","html_url":"https://github.com/chidiwilliams/GPT-Automator","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/chidiwilliams%2FGPT-Automator","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/chidiwilliams%2FGPT-Automator/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/chidiwilliams%2FGPT-Automator/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/chidiwilliams%2FGPT-Automator/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/chidiwilliams","download_url":"https://codeload.github.com/chidiwilliams/GPT-Automator/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":223273418,"owners_count":17117801,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","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":["automator","gpt-3","langchain","macos"],"created_at":"2024-08-01T15:04:43.477Z","updated_at":"2025-04-07T06:32:29.296Z","avatar_url":"https://github.com/chidiwilliams.png","language":"Python","readme":"# GPT Automator\n\n![App](assets/app.png)\n\nYour voice-controlled Mac assistant. GPT Automator lets you perform tasks on your Mac using your voice. For example, opening applications, looking up restaurants, and synthesizing information.\n\nMade by [Luke Harries](https://harries.co/) and [Chidi Williams](https://chidiwilliams.com/) at\nthe [London EA Hackathon, February 2023](https://forum.effectivealtruism.org/events/gTSwA8RoGidjpLnf6/london-ea-hackathon).\n\n[![GPT Automator demo](https://cdn.loom.com/sessions/thumbnails/7bfa82c604f3412fbbb04191ce2ae12f-00001.gif)](https://www.loom.com/share/7bfa82c604f3412fbbb04191ce2ae12f \"GPT Automator demo\")\n\n## Requirements\n\n* [FFmpeg](https://ffmpeg.org/)\n\n   ```shell\n   # on Ubuntu or Debian\n   sudo apt update \u0026\u0026 sudo apt install ffmpeg\n\n   # on Arch Linux\n   sudo pacman -S ffmpeg\n\n   # on MacOS using Homebrew (https://brew.sh/)\n   brew install ffmpeg\n\n   # on Windows using Chocolatey (https://chocolatey.org/)\n   choco install ffmpeg\n\n   # on Windows using Scoop (https://scoop.sh/)\n   scoop install ffmpeg\n   ```\n\n## Instructions\n\n1. Install the dependencies from the `requirements.txt` or `pyproject.toml` files.\n2. Create a `.env` file from the `.env.example` file and fill in the OpenAI API key.\n3. Run `python gui.py` to run the GUI and click 'Record' to say your prompt. Alternatively,\n   run `python main.py [prompt]`\n   to run the CLI.\n\n## How it works\n\nGPT Automator converts your audio input to text using OpenAI's Whisper. Then, it uses a [LangChain](https://github.com/hwchase17/langchain) Agent to choose a set of actions, including generating AppleScript (for desktop automation) and\nJavaScript (for browser automation) commands from your prompt using OpenAI's GPT-3 (\"text-davinci-003\"),\nand then executing the resulting script.\n\n## Example prompts\n\n* Find the result of a calculation. Prompt: \"What is 2 + 2?\" -\u003e It will write AppleScript to open up a calculator and type in 5 * 5.\n* Find restaurants nearby. Prompt: \"Find restaurants near me\" -\u003e It will open up Google search, read the text on the page, and say the best restaurants.\n* Play a game of chess. Prompt: \"Play a game of chess\" -\u003e It will open up Chess.com and start clicking around.\n\n## Learn more\n\nCheckout our blog posts for more information:\n- [Chidi's blog post](https://chidiwilliams.com/post/gpt-automator/)\n- [Luke's blog post](https://harries.co/ea-hackathon-gpt-automator-and-langchain/)\n\n## Disclaimer\n\nThis project executes code generated from natural language and may be susceptible\nto [prompt injection](https://en.wikipedia.org/wiki/Prompt_engineering#Prompt_injection) and similar\nattacks. This work was made as a proof-of-concept and is not intended for production use.\n","funding_links":[],"categories":["Python","Open Source Projects","开源项目"],"sub_categories":["Other / Chatbots","其他聊天机器人"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fchidiwilliams%2FGPT-Automator","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fchidiwilliams%2FGPT-Automator","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fchidiwilliams%2FGPT-Automator/lists"}