[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-71184":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":8,"htmlUrl":8,"language":9,"languages":8,"totalLinesOfCode":8,"stars":10,"forks":11,"watchers":12,"openIssues":13,"contributorsCount":14,"subscribersCount":14,"size":14,"stars1d":14,"stars7d":14,"stars30d":14,"stars90d":14,"forks30d":14,"starsTrendScore":14,"compositeScore":15,"rankGlobal":8,"rankLanguage":8,"license":16,"archived":17,"fork":17,"defaultBranch":18,"hasWiki":17,"hasPages":17,"topics":19,"createdAt":8,"pushedAt":8,"updatedAt":20,"readmeContent":21,"aiSummary":22,"trendingCount":14,"starSnapshotCount":14,"syncStatus":23,"lastSyncTime":24,"discoverSource":25},71184,"wolverine","biobootloader\u002Fwolverine","biobootloader",null,"Python",5085,615,80,17,0,61.37,"MIT License",false,"main",[],"2026-06-12 04:00:59","# DEPRECATED: Try Mentat instead! https:\u002F\u002Fgithub.com\u002FAbanteAI\u002Fmentat\n\n\n# Wolverine\n\n## About\n\nGive your python scripts regenerative healing abilities!\n\nRun your scripts with Wolverine and when they crash, GPT-4 edits them and explains what went wrong. Even if you have many bugs it will repeatedly rerun until it's fixed.\n\nFor a quick demonstration see my [demo video on twitter](https:\u002F\u002Ftwitter.com\u002Fbio_bootloader\u002Fstatus\u002F1636880208304431104).\n\n## Setup\n\n    python3 -m venv venv\n    source venv\u002Fbin\u002Factivate\n    pip install -r requirements.txt\n    cp .env.sample .env\n\nAdd your openAI api key to `.env`\n\n_warning!_ By default wolverine uses GPT-4 and may make many repeated calls to the api.\n\n## Example Usage\n\nTo run with gpt-4 (the default, tested option):\n\n    python -m wolverine examples\u002Fbuggy_script.py \"subtract\" 20 3\n\nYou can also run with other models, but be warned they may not adhere to the edit format as well:\n\n    python -m wolverine --model=gpt-3.5-turbo examples\u002Fbuggy_script.py \"subtract\" 20 3\n\nIf you want to use GPT-3.5 by default instead of GPT-4 uncomment the default model line in `.env`:\n\n    DEFAULT_MODEL=gpt-3.5-turbo\n\nYou can also use flag `--confirm=True` which will ask you `yes or no` before making changes to the file. If flag is not used then it will apply the changes to the file\n\n    python -m wolverine examples\u002Fbuggy_script.py \"subtract\" 20 3 --confirm=True\n\n## Environment variables\n\n| env name            | description                                                       | default value |\n| ------------------- | ----------------------------------------------------------------- | ------------- |\n| OPENAI_API_KEY      | OpenAI API key                                                    | None          |\n| DEFAULT_MODEL       | GPT model to use                                                  | \"gpt-4\"       |\n| VALIDATE_JSON_RETRY | Number of retries when requesting OpenAI API (-1 means unlimites) | -1            |\n\n## Future Plans\n\nThis is just a quick prototype I threw together in a few hours. There are many possible extensions and contributions are welcome:\n\n- add flags to customize usage, such as asking for user confirmation before running changed code\n- further iterations on the edit format that GPT responds in. Currently it struggles a bit with indentation, but I'm sure that can be improved\n- a suite of example buggy files that we can test prompts on to ensure reliability and measure improvement\n- multiple files \u002F codebases: send GPT everything that appears in the stacktrace\n- graceful handling of large files - should we just send GPT relevant classes \u002F functions?\n- extension to languages other than python\n\n## Star History\n\n[![Star History Chart](https:\u002F\u002Fapi.star-history.com\u002Fsvg?repos=biobootloader\u002Fwolverine&type=Date)](https:\u002F\u002Fstar-history.com\u002F#biobootloader\u002Fwolverine)\n","Wolverine 是一个能够自动修复 Python 脺脚本错误的工具。它通过调用 GPT-4 来识别并修正代码中的问题，即使存在多个错误也能反复运行直至修复完成。用户可以通过简单的命令行操作启动 Wolverine，并且支持自定义 OpenAI API 密钥、默认使用的 GPT 模型等环境变量设置。此外，还可以选择开启确认模式，在修改文件前询问用户是否同意。此项目适用于需要快速调试和修复 Python 代码的场景，特别适合那些希望减少手动调试时间的开发者。尽管目前仅支持 Python，但未来计划扩展到其他编程语言。",2,"2026-06-11 03:36:28","high_star"]