GitHub项目：Agentless
仓库地址：https://github.com/OpenAutoCoder/Agentless
Stars：2108 | 作者：OpenAutoCoder
项目描述：Agentless🐱：一种自动解决软件开发问题的无代理方法
===================================================
自述文件内容：
# 😺 Agentless
😽新闻 |
🐈设置 |
🧶比较 |
🐈⬛Artifacts |
📝Citation |
😻Acknowledgement
## 😽 News
- *Dec 2nd, 2024*: We integrated Agentless with Claude 3.5 Sonnet to achieve 40.7% and 50.8% solve rate on SWE-bench lite and verified
- *2024 年 10 月 28 日*：我们刚刚发布了 OpenAutoCoder-Agentless 1.5！
- *2024 年 7 月 1 日*：我们刚刚发布了 OpenAutoCoder-Agentless 1.0！ **Agentless** currently is the best open-source approach on SWE-bench lite with 82 fixes (27.3%) and costing on average $0.34 per issue.
## 😺 About
**无代理**是一种自动解决软件开发问题的“无代理”方法。 To solve each issue, **Agentless** follows a simple three phase process: localization, repair, and patch validation.
- 🙀 **本地化**：Agentless 采用分层流程，首先将故障定位到特定文件，然后定位到相关类或函数，最后定位到细粒度的编辑位置
- 😼 **Repair**: Agentless takes the edit locations and samples multiple candidate patches per bug in a simple diff format
- 😸 **补丁验证**：Agentless 选择要运行的回归测试并生成额外的再现测试来再现原始错误。使用测试结果，Agentless 对所有剩余补丁重新排序，选择一个进行提交
## 🐈 Setup
首先创建环境
````外壳
git 克隆 https://github.com/OpenAutoCoder/Agentless.git
cd Agentless
conda create -n 无代理 python=3.11
conda activate agentless
pip install -r 要求.txt
导出 PYTHONPATH=$PYTHONPATH:$(pwd)
````
<详细信息><摘要>⏬ 开发者设置
````外壳
# for contribution, please install the pre-commit hook.
pre-commit install # this allows a more standardized code style
````
然后导出您的 OpenAI API 密钥
```shell
导出 OPENAI_API_KEY={key_here}
````
Now you are ready to run **Agentless** on the problems in SWE-bench!
> [!NOTE]
>
> To reproduce the full SWE-bench lite experiments and follow our exact setup as described in the paper. Please see this [README](https://github.com/OpenAutoCoder/Agentless/blob/main/README_swebench.md)
## 🧶 Comparison
Below shows the comparison graph between **Agentless** and the best open-source agent-based approaches on SWE-bench lite
## 🐈⬛ Artifacts
你