{"id":26896175,"url":"https://github.com/princeton-nlp/SWE-agent","last_synced_at":"2025-04-01T03:01:10.851Z","repository":{"id":231050049,"uuid":"780737106","full_name":"SWE-agent/SWE-agent","owner":"SWE-agent","description":"[NeurIPS 2024] SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges.","archived":false,"fork":false,"pushed_at":"2024-12-07T22:18:37.000Z","size":37192,"stargazers_count":13821,"open_issues_count":21,"forks_count":1402,"subscribers_count":99,"default_branch":"main","last_synced_at":"2024-12-07T22:25:07.991Z","etag":null,"topics":["agent","agent-based-model","ai","cybersecurity","developer-tools","llm","lms"],"latest_commit_sha":null,"homepage":"https://swe-agent.com","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/SWE-agent.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":".github/CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":"SECURITY.md","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-04-02T04:09:47.000Z","updated_at":"2024-12-07T22:18:13.000Z","dependencies_parsed_at":"2024-07-17T16:54:07.429Z","dependency_job_id":"d35d4b9e-6c2a-4061-a346-aa88f93075f8","html_url":"https://github.com/SWE-agent/SWE-agent","commit_stats":null,"previous_names":["princeton-nlp/swe-agent","swe-agent/swe-agent"],"tags_count":10,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SWE-agent%2FSWE-agent","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SWE-agent%2FSWE-agent/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SWE-agent%2FSWE-agent/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SWE-agent%2FSWE-agent/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/SWE-agent","download_url":"https://codeload.github.com/SWE-agent/SWE-agent/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246574829,"owners_count":20799221,"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":["agent","agent-based-model","ai","cybersecurity","developer-tools","llm","lms"],"created_at":"2025-04-01T03:01:03.557Z","updated_at":"2025-04-01T03:01:10.816Z","avatar_url":"https://github.com/SWE-agent.png","language":"Python","funding_links":[],"categories":["Autonomous Coding Agents","[SWE Agent](https://github.com/princeton-nlp/SWE-agent)","AI Сервисы для разработки ПО","🏗️ Reference Implementations \u0026 Case Studies","Tools \u0026 Agents","🤖 AI Agents","Coding Agents \u0026 Platforms","Repos","Learning","Tools \u0026 Frameworks","\u003cspan id=\"game\"\u003eGame (World Model \u0026 Agent)\u003c/span\u003e","AI Agent","🖥 Coding Agents","ai","Coding Agents","🚀 Specialized Agents","🕵️ 智能体（Agents）","Agent Categories","3. Coding Agents","1. Local Agents","Development Workflows \u0026 Agents","Applications","ツール","Frameworks \u0026 Libraries","Infrastructure and Tools","AI Agents"],"sub_categories":["Links","Генераторы ПО “с нуля” и AI-разработчики","T5 · Autonomous SWE Agents","Open Source Projects","Repositories","Agent","\u003cspan id=\"tool\"\u003eLLM (LLM \u0026 Tool)\u003c/span\u003e","Task","Autonomous Software Engineers","💻 Coding Agents","Agent 应用案例","\u003ca name=\"Unclassified\"\u003e\u003c/a\u003eUnclassified","Enterprise Agent Platforms","Coding Agents \u0026 IDE Extensions","Other IDEs","Autonomous Agent Task Solver Projects","Community","エージェント型コーディング環境","Code Agents","Agents and Swarms"],"readme":"\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://swe-agent.com/latest/\"\u003e\n    \u003cimg src=\"assets/swe-agent-banner.png\" alt=\"swe-agent.com\" style=\"height: 12em\" /\u003e\n  \u003c/a\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://swe-agent.com/latest/\"\u003e\u003cstrong\u003eDocumentation\u003c/strong\u003e\u003c/a\u003e\u0026nbsp; | \u0026nbsp;\n  \u003ca href=\"https://discord.gg/AVEFbBn2rH\"\u003e\u003cstrong\u003eDiscord\u003c/strong\u003e\u003c/a\u003e\u0026nbsp; | \u0026nbsp;\n  \u003ca href=\"https://arxiv.org/abs/2405.15793\"\u003e\u003cstrong\u003ePaper\u003c/strong\u003e\u003c/a\u003e\n\u003c/p\u003e\n\n\nSWE-agent lets your language model of choice (e.g. GPT-4o or Claude Sonnet 3.7) autonomously use tools to:\n\n* [fix issues in real GitHub repositories](https://swe-agent.com/latest/usage/hello_world),\n* perform tasks on the web,\n* find cybersecurity vulnerabilities (by solving Capture The Flag challenges), or\n* [any custom task](https://swe-agent.com/latest/usage/coding_challenges).\n\nIt does so by using configurable [agent-computer interfaces](https://arxiv.org/abs/2405.15793) (ACIs) to interact with isolated computer environments.\n\nSWE-agent is built and maintained by researchers from Princeton University and Stanford University.\n\n## 📣 News\n\n* Feb 28: [SWE-agent 1.0 + Claude 3.7 is SoTA on SWE-Bench full](https://x.com/KLieret/status/1895487966409298067)\n* Feb 25: [SWE-agent 1.0 + Claude 3.7 is SoTA on SWE-bench verified](https://x.com/KLieret/status/1894408819670733158)\n* Feb 13: [Releasing SWE-agent 1.0: SoTA on SWE-bench light \u0026 tons of new features](https://x.com/KLieret/status/1890048205448220849)\n* Dec 7: [An interview with the SWE-agent \u0026 SWE-bench team](https://www.youtube.com/watch?v=fcr8WzeEXyk)\n\n## 🚀 Get started!\n\n👉 Try SWE-agent in your browser: [![Open in GitHub Codespaces](https://img.shields.io/badge/Open_in_GitHub_Codespaces-gray?logo=github)](https://codespaces.new/SWE-agent/SWE-agent) ([more information](https://swe-agent.com/latest/installation/codespaces/))\n\nRead our [documentation][docs] to learn more:\n\n* [Installation](https://swe-agent.com/latest/installation/source/)\n* [Hello world from the command line](https://swe-agent.com/latest/usage/hello_world/)\n* [Benchmarking on SWE-bench](https://swe-agent.com/latest/usage/batch_mode/)\n* [Frequently Asked Questions](https://swe-agent.com/latest/faq/)\n\n[docs]: https://swe-agent.com\n\n## SWE-agent for offensive cybersecurity (EnIGMA) \u003ca name=\"enigma\"\u003e\u003c/a\u003e\n\n\u003cimg src=\"https://github.com/user-attachments/assets/84599168-11a7-4776-8a49-33dbf0758bb2\" height=\"80px\"\u003e\u003c/img\u003e\n\n[SWE-agent: EnIGMA][enigma] is a mode for solving offensive cybersecurity (capture the flag) challenges.\nEnIGMA achieves state-of-the-art results on multiple cybersecurity benchmarks (see [leaderboard](https://enigma-agent.com/#results)).\nThe EnIGMA project introduced multiple features that are available in all modes of SWE-agent, such as the [debugger and server connection tools](https://swe-agent.com/0.7/background/iat/) and a [summarizer](https://swe-agent.com/0.7/config/summarizers/) to handle long outputs. Please use [SWE-agent 0.7](https://github.com/SWE-agent/SWE-agent/tree/v0.7) while we update EnIGMA for 1.0.\n\n[enigma]: https://enigma-agent.com\n[SWE-bench]: https://github.com/SWE-bench/SWE-bench\n[nyu-ctf]: https://arxiv.org/abs/2406.05590\n\n## About\nSWE-agent is an academic project started at Princeton University by John Yang*, Carlos E. Jimenez*, Alexander Wettig, Kilian Lieret, Shunyu Yao, Karthik Narasimhan, and Ofir Press.\nContact person: [John Yang](https://john-b-yang.github.io/), [Carlos E. Jimenez](http://www.carlosejimenez.com/), and [Kilian Lieret](https://www.lieret.net/) (Email: johnby@stanford.edu, carlosej@princeton.edu, kl5675@princeton.edu).\n\n## Contributions \u003ca name=\"contributions\"\u003e\u003c/a\u003e\n\n- If you'd like to ask questions, learn about upcoming features, and participate in future development, join our [Discord community](https://discord.gg/AVEFbBn2rH)!\n- If you'd like to contribute to the codebase, we welcome [issues](https://github.com/SWE-agent/SWE-agent/issues) and [pull requests](https://github.com/SWE-agent/SWE-agent/pulls)!\n\n## Citation \u003ca name=\"citation\"\u003e\u003c/a\u003e\n\nIf you found this work helpful, please consider citing it using the following:\n```bibtex\n@inproceedings{yang2024sweagent,\n  title={{SWE}-agent: Agent-Computer Interfaces Enable Automated Software Engineering},\n  author={John Yang and Carlos E Jimenez and Alexander Wettig and Kilian Lieret and Shunyu Yao and Karthik R Narasimhan and Ofir Press},\n  booktitle={The Thirty-eighth Annual Conference on Neural Information Processing Systems},\n  year={2024},\n  url={https://arxiv.org/abs/2405.15793}\n}\n```\n\nIf you used the summarizer, interactive commands or the offensive cybersecurity capabilities in SWE-agent, please also consider citing:\n```bibtex\n@misc{abramovich2024enigmaenhancedinteractivegenerative,\n      title={EnIGMA: Enhanced Interactive Generative Model Agent for CTF Challenges},\n      author={Talor Abramovich and Meet Udeshi and Minghao Shao and Kilian Lieret and Haoran Xi and Kimberly Milner and Sofija Jancheska and John Yang and Carlos E. Jimenez and Farshad Khorrami and Prashanth Krishnamurthy and Brendan Dolan-Gavitt and Muhammad Shafique and Karthik Narasimhan and Ramesh Karri and Ofir Press},\n      year={2024},\n      eprint={2409.16165},\n      archivePrefix={arXiv},\n      primaryClass={cs.AI},\n      url={https://arxiv.org/abs/2409.16165},\n}\n```\n\n## 🪪 License \u003ca name=\"license\"\u003e\u003c/a\u003e\nMIT. Check `LICENSE`.\n\n\u003cdiv align=\"center\"\u003e\n\n[![Pytest](https://github.com/SWE-agent/SWE-agent/actions/workflows/pytest.yaml/badge.svg)](https://github.com/SWE-agent/SWE-agent/actions/workflows/pytest.yaml)\n[![build-docs](https://github.com/SWE-agent/SWE-agent/actions/workflows/build-docs.yaml/badge.svg)](https://github.com/SWE-agent/SWE-agent/actions/workflows/build-docs.yaml)\n[![codecov](https://codecov.io/gh/SWE-agent/SWE-agent/graph/badge.svg?token=18XAVDK365)](https://codecov.io/gh/SWE-agent/SWE-agent)\n[![pre-commit.ci status](https://results.pre-commit.ci/badge/github/SWE-agent/SWE-agent/main.svg)](https://results.pre-commit.ci/latest/github/SWE-agent/SWE-agent/main)\n[![Markdown links](https://github.com/SWE-agent/SWE-agent/actions/workflows/check-links.yaml/badge.svg)](https://github.com/SWE-agent/SWE-agent/actions/workflows/check-links.yaml)\n\n\u003c/div\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fprinceton-nlp%2FSWE-agent","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fprinceton-nlp%2FSWE-agent","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fprinceton-nlp%2FSWE-agent/lists"}