Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/OpenAutoCoder/Agentless
Agentless🐱: an agentless approach to automatically solve software development problems
https://github.com/OpenAutoCoder/Agentless
agent artificial-intelligence llm software-development
Last synced: 3 months ago
JSON representation
Agentless🐱: an agentless approach to automatically solve software development problems
- Host: GitHub
- URL: https://github.com/OpenAutoCoder/Agentless
- Owner: OpenAutoCoder
- License: mit
- Created: 2024-06-30T23:37:17.000Z (8 months ago)
- Default Branch: main
- Last Pushed: 2024-10-29T02:00:47.000Z (4 months ago)
- Last Synced: 2024-10-29T02:33:14.987Z (4 months ago)
- Topics: agent, artificial-intelligence, llm, software-development
- Language: Python
- Homepage:
- Size: 576 KB
- Stars: 696
- Watchers: 7
- Forks: 83
- Open Issues: 23
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- awesome-AI-driven-development - Agentless - an agentless approach to automatically solve software development problems (Uncategorized / Uncategorized)
- project-awesome - OpenAutoCoder/Agentless - Agentless🐱: an agentless approach to automatically solve software development problems (Python)
- Awesome-Local-LLM - Git
- Awesome-Local-LLM - Git
- awesome - OpenAutoCoder/Agentless - Agentless🐱: an agentless approach to automatically solve software development problems (Python)
README
# 😺 Agentless
😽News |
🐈Setup |
🧶Comparison |
🐈⬛Artifacts |
📝Citation |
😻Acknowledgement
## 😽 News
- *Oct 28th, 2024*: We just released OpenAutoCoder-Agentless 1.5!
- *July 1st, 2024*: We just released 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 $0.34 per issue.
## 😺 About
**Agentless** is an *agentless* approach to automatically solve software development problems. To solve each issue, **Agentless** follows a simple three phase process: localization, repair, and patch validation.
- 🙀 **Localization**: Agentless employs a hierarchical process to first localize the fault to specific files, then to relevant classes or functions, and finally to fine-grained edit locations
- 😼 **Repair**: Agentless takes the edit locations and samples multiple candidate patches per bug in a simple diff format
- 😸 **Patch Validation**: Agentless selects the regression tests to run and generates additional reproduction test to reproduce the original error. Using the test results, Agentless re-ranks all remaining patches to selects one to submit
## 🐈 Setup
First create the environment
```shell
git clone https://github.com/OpenAutoCoder/Agentless.git
cd Agentless
conda create -n agentless python=3.11
conda activate agentless
pip install -r requirements.txt
export PYTHONPATH=$PYTHONPATH:$(pwd)
```
⏬ Developer Setup
```shell
# for contribution, please install the pre-commit hook.
pre-commit install # this allows a more standardized code style
```
Then export your OpenAI API key
```shell
export 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
You can download the complete artifacts of **Agentless** in our [v1.5.0 release](https://github.com/OpenAutoCoder/Agentless/releases/tag/v1.5.0):
- 🐈⬛ agentless_swebench_lite: complete Agentless run on SWE-bench Lite
- 🐈⬛ agentless_swebench_verified: complete Agentless run on SWE-bench Verified
- 🐈⬛ swebench_repo_structure: preprocessed structure information for each SWE-Bench problem
You can also checkout `classification/` folder to obtain our manual classifications of SWE-bench-lite as well as our filtered SWE-bench-lite-*S* problems.
## 📝 Citation
```bibtex
@article{agentless,
author = {Xia, Chunqiu Steven and Deng, Yinlin and Dunn, Soren and Zhang, Lingming},
title = {Agentless: Demystifying LLM-based Software Engineering Agents},
year = {2024},
journal = {arXiv preprint},
}
```
> [!NOTE]
>
> The first two authors contributed equally to this work, with author order determined via [*Nigiri*](https://senseis.xmp.net/?Nigiri)
## 😻 Acknowledgement
* [SWE-bench](https://www.swebench.com/)
* [Aider](https://github.com/paul-gauthier/aider)
* [SWE-bench-docker](https://github.com/aorwall/SWE-bench-docker)