[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-588":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":17,"stars30d":18,"stars90d":16,"forks30d":16,"starsTrendScore":19,"compositeScore":20,"rankGlobal":10,"rankLanguage":10,"license":21,"archived":22,"fork":23,"defaultBranch":24,"hasWiki":23,"hasPages":23,"topics":25,"createdAt":10,"pushedAt":10,"updatedAt":35,"readmeContent":36,"aiSummary":37,"trendingCount":16,"starSnapshotCount":16,"syncStatus":17,"lastSyncTime":38,"discoverSource":39},588,"gpt-engineer","AntonOsika\u002Fgpt-engineer","AntonOsika","CLI platform to experiment with codegen. Precursor to: https:\u002F\u002Flovable.dev","",null,"Python",55201,7312,527,32,0,2,14,6,45,"MIT License",true,false,"main",[26,27,28,29,30,31,32,5,33,34],"ai","autonomous-agent","code-generation","codebase-generation","codegen","coding-assistant","gpt-4","openai","python","2026-06-12 02:00:15","# gpt-engineer\n\n[![GitHub Repo stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fgpt-engineer-org\u002Fgpt-engineer?style=social)](https:\u002F\u002Fgithub.com\u002Fgpt-engineer-org\u002Fgpt-engineer)\n[![Discord Follow](https:\u002F\u002Fdcbadge.vercel.app\u002Fapi\u002Fserver\u002F8tcDQ89Ej2?style=flat)](https:\u002F\u002Fdiscord.gg\u002F8tcDQ89Ej2)\n[![License](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flicense\u002Fgpt-engineer-org\u002Fgpt-engineer)](https:\u002F\u002Fgithub.com\u002Fgpt-engineer-org\u002Fgpt-engineer\u002Fblob\u002Fmain\u002FLICENSE)\n[![GitHub Issues or Pull Requests](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fissues\u002Fgpt-engineer-org\u002Fgpt-engineer)](https:\u002F\u002Fgithub.com\u002Fgpt-engineer-org\u002Fgpt-engineer\u002Fissues)\n![GitHub Release](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fv\u002Frelease\u002Fgpt-engineer-org\u002Fgpt-engineer)\n[![Twitter Follow](https:\u002F\u002Fimg.shields.io\u002Ftwitter\u002Ffollow\u002Fantonosika?style=social)](https:\u002F\u002Ftwitter.com\u002Fantonosika)\n\nThe OG code genereation experimentation platform!\n\nIf you are looking for the evolution that is an opinionated, managed service – check out gptengineer.app.\n\nIf you are looking for a well maintained hackable CLI for – check out aider.\n\n\ngpt-engineer lets you:\n- Specify software in natural language\n- Sit back and watch as an AI writes and executes the code\n- Ask the AI to implement improvements\n\n## Getting Started\n\n### Install gpt-engineer\n\nFor **stable** release:\n\n- `python -m pip install gpt-engineer`\n\nFor **development**:\n- `git clone https:\u002F\u002Fgithub.com\u002Fgpt-engineer-org\u002Fgpt-engineer.git`\n- `cd gpt-engineer`\n- `poetry install`\n- `poetry shell` to activate the virtual environment\n\nWe actively support Python 3.10 - 3.12. The last version to support Python 3.8 - 3.9 was [0.2.6](https:\u002F\u002Fpypi.org\u002Fproject\u002Fgpt-engineer\u002F0.2.6\u002F).\n\n### Setup API key\n\nChoose **one** of:\n- Export env variable (you can add this to .bashrc so that you don't have to do it each time you start the terminal)\n    - `export OPENAI_API_KEY=[your api key]`\n- .env file:\n    - Create a copy of `.env.template` named `.env`\n    - Add your OPENAI_API_KEY in .env\n- Custom model:\n    - See [docs](https:\u002F\u002Fgpt-engineer.readthedocs.io\u002Fen\u002Flatest\u002Fopen_models.html), supports local model, azure, etc.\n\nCheck the [Windows README](.\u002FWINDOWS_README.md) for Windows usage.\n\n**Other ways to run:**\n- Use Docker ([instructions](docker\u002FREADME.md))\n- Do everything in your browser:\n[![Open in GitHub Codespaces](https:\u002F\u002Fgithub.com\u002Fcodespaces\u002Fbadge.svg)](https:\u002F\u002Fgithub.com\u002Fgpt-engineer-org\u002Fgpt-engineer\u002Fcodespaces)\n\n### Create new code (default usage)\n- Create an empty folder for your project anywhere on your computer\n- Create a file called `prompt` (no extension) inside your new folder and fill it with instructions\n- Run `gpte \u003Cproject_dir>` with a relative path to your folder\n  - For example: `gpte projects\u002Fmy-new-project` from the gpt-engineer directory root with your new folder in `projects\u002F`\n\n### Improve existing code\n- Locate a folder with code which you want to improve anywhere on your computer\n- Create a file called `prompt` (no extension) inside your new folder and fill it with instructions for how you want to improve the code\n- Run `gpte \u003Cproject_dir> -i` with a relative path to your folder\n  - For example: `gpte projects\u002Fmy-old-project -i` from the gpt-engineer directory root with your folder in `projects\u002F`\n\n### Benchmark custom agents\n- gpt-engineer installs the binary 'bench', which gives you a simple interface for benchmarking your own agent implementations against popular public datasets.\n- The easiest way to get started with benchmarking is by checking out the [template](https:\u002F\u002Fgithub.com\u002Fgpt-engineer-org\u002Fgpte-bench-template) repo, which contains detailed instructions and an agent template.\n- Currently supported benchmark:\n  - [APPS](https:\u002F\u002Fgithub.com\u002Fhendrycks\u002Fapps)\n  - [MBPP](https:\u002F\u002Fgithub.com\u002Fgoogle-research\u002Fgoogle-research\u002Ftree\u002Fmaster\u002Fmbpp)\n\nThe community has started work with different benchmarking initiatives, as described in [this Loom](https:\u002F\u002Fwww.loom.com\u002Fshare\u002F206805143fbb4302b5455a5329eaab17?sid=f689608f-8e49-44f7-b55f-4c81e9dc93e6) video.\n\n### Research\nSome of our community members have worked on different research briefs that could be taken further. See [this document](https:\u002F\u002Fdocs.google.com\u002Fdocument\u002Fd\u002F1qmOj2DvdPc6syIAm8iISZFpfik26BYw7ZziD5c-9G0E\u002Fedit?usp=sharing) if you are interested.\n\n## Terms\nBy running gpt-engineer, you agree to our [terms](https:\u002F\u002Fgithub.com\u002Fgpt-engineer-org\u002Fgpt-engineer\u002Fblob\u002Fmain\u002FTERMS_OF_USE.md).\n\n\n## Relation to gptengineer.app (GPT Engineer)\n[gptengineer.app](https:\u002F\u002Fgptengineer.app\u002F) is a commercial project for the automatic generation of web apps.\nIt features a UI for non-technical users connected to a git-controlled codebase.\nThe gptengineer.app team is actively supporting the open source community.\n\n\n## Features\n\n### Pre Prompts\nYou can specify the \"identity\" of the AI agent by overriding the `preprompts` folder with your own version of the `preprompts`. You can do so via the `--use-custom-preprompts` argument.\n\nEditing the `preprompts` is how you make the agent remember things between projects.\n\n### Vision\n\nBy default, gpt-engineer expects text input via a `prompt` file. It can also accept image inputs for vision-capable models. This can be useful for adding UX or architecture diagrams as additional context for GPT Engineer. You can do this by specifying an image directory with the `—-image_directory` flag and setting a vision-capable model in the second CLI argument.\n\nE.g. `gpte projects\u002Fexample-vision gpt-4-vision-preview --prompt_file prompt\u002Ftext --image_directory prompt\u002Fimages -i`\n\n### Open source, local and alternative models\n\nBy default, gpt-engineer supports OpenAI Models via the OpenAI API or Azure OpenAI API, as well as Anthropic models.\n\nWith a little extra setup, you can also run with open source models like WizardCoder. See the [documentation](https:\u002F\u002Fgpt-engineer.readthedocs.io\u002Fen\u002Flatest\u002Fopen_models.html) for example instructions.\n\n## Mission\n\nThe gpt-engineer community mission is to **maintain tools that coding agent builders can use and facilitate collaboration in the open source community**.\n\nIf you are interested in contributing to this, we are interested in having you.\n\nIf you want to see our broader ambitions, check out the [roadmap](https:\u002F\u002Fgithub.com\u002Fgpt-engineer-org\u002Fgpt-engineer\u002Fblob\u002Fmain\u002FROADMAP.md), and join\n[discord](https:\u002F\u002Fdiscord.gg\u002F8tcDQ89Ej2)\nto learn how you can [contribute](.github\u002FCONTRIBUTING.md) to it.\n\ngpt-engineer is [governed](https:\u002F\u002Fgithub.com\u002Fgpt-engineer-org\u002Fgpt-engineer\u002Fblob\u002Fmain\u002FGOVERNANCE.md) by a board of long-term contributors. If you contribute routinely and have an interest in shaping the future of gpt-engineer, you will be considered for the board.\n\n## Significant contributors\n\u003Cul style=\"list-style-type: none; padding: 0; display: flex; flex-wrap: wrap;\"> \u003Cli style=\"margin-right: 10px; margin-bottom: 10px;\"> \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FATheorell\"> \u003Cimg src=\"https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F143704446?s=64&v=4\" alt=\"@ATheorell\" width=\"32\" height=\"32\" style=\"border-radius: 50%;\"> @ATheorell \u003C\u002Fa> \u003C\u002Fli> \u003Cli style=\"margin-right: 10px; margin-bottom: 10px;\"> \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fsimilato87\"> \u003Cimg src=\"https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F71301573?s=64&v=4\" alt=\"@similato87\" width=\"32\" height=\"32\" style=\"border-radius: 50%;\"> @similato87 \u003C\u002Fa> \u003C\u002Fli> \u003Cli style=\"margin-right: 10px; margin-bottom: 10px;\"> \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FTheoMcCabe\"> \u003Cimg src=\"https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F9841960?s=64&v=4\" alt=\"@TheoMcCabe\" width=\"32\" height=\"32\" style=\"border-radius: 50%;\"> @TheoMcCabe \u003C\u002Fa> \u003C\u002Fli> \u003Cli style=\"margin-right: 10px; margin-bottom: 10px;\"> \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fcaptivus\"> \u003Cimg src=\"https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F366332?s=64&v=4\" alt=\"@captivus\" width=\"32\" height=\"32\" style=\"border-radius: 50%;\"> @captivus \u003C\u002Fa> \u003C\u002Fli> \u003C\u002Ful>\n\n\n## Example\n\n\n\nhttps:\u002F\u002Fgithub.com\u002Fgpt-engineer-org\u002Fgpt-engineer\u002Fassets\u002F4467025\u002F40d0a9a8-82d0-4432-9376-136df0d57c99\n","gpt-engineer 是一个用于代码生成实验的CLI平台。它允许用户以自然语言描述软件需求，然后通过AI自动生成并执行相应的代码，并且可以请求AI对代码进行改进。该项目采用Python编写，支持使用OpenAI API来驱动代码生成过程，同时也提供了对本地模型和其他云服务的支持。适合开发者在快速原型开发、代码辅助生成以及自动化编程任务中使用，能够显著提高编码效率和创新速度。","2026-06-11 02:37:52","top_all"]