{"id":26932071,"url":"https://github.com/BigComputer-Project/SWE-Arena","last_synced_at":"2025-04-02T08:02:19.755Z","repository":{"id":276619534,"uuid":"866072103","full_name":"BigComputer-Project/SWE-Arena","owner":"BigComputer-Project","description":"SWE Arena","archived":false,"fork":false,"pushed_at":"2025-03-22T23:53:27.000Z","size":57497,"stargazers_count":27,"open_issues_count":10,"forks_count":3,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-03-23T00:24:46.047Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"https://swe-arena.com/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/BigComputer-Project.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-10-01T15:47:10.000Z","updated_at":"2025-03-16T09:34:32.000Z","dependencies_parsed_at":"2025-03-23T00:33:10.972Z","dependency_job_id":null,"html_url":"https://github.com/BigComputer-Project/SWE-Arena","commit_stats":null,"previous_names":["bigcomputer-project/swe-arena"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BigComputer-Project%2FSWE-Arena","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BigComputer-Project%2FSWE-Arena/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BigComputer-Project%2FSWE-Arena/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BigComputer-Project%2FSWE-Arena/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/BigComputer-Project","download_url":"https://codeload.github.com/BigComputer-Project/SWE-Arena/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246777834,"owners_count":20832032,"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":[],"created_at":"2025-04-02T08:00:56.595Z","updated_at":"2025-04-02T08:02:19.743Z","avatar_url":"https://github.com/BigComputer-Project.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"# SWE Arena\n| [**Live Demo**](https://swe-arena.com) | [**X**](https://x.com/BigComProject) | [**Discord**](https://discord.gg/auCweVA9hB) | [**GitHub**](https://github.com/BigComputer-Project/SWE-Arena) |\n\nSWE Arena is an open-source platform that extends [FastChat](https://github.com/lm-sys/FastChat) with powerful code execution capabilities, enabling direct evaluation of LLM-generated programs across a wide range of outputs - from simple computations to complex visual interfaces. Building upon the FastChat project, it provides a secure sandbox environment for running and evaluating AI-generated visual interfaces.\n\n\nSWE Arena belongs to [Big Computer Project](https://bigcomputer-project.github.io/), an [AI Alliance](https://thealliance.ai/) project focused on building the next generation of large language models for software engineering.\n\n## News\n[2025/02] We have partnered with [Hugging Face](https://huggingface.co/) to shape the future of dynamic evaluation in automated software engineering.\n[2025/02] We released SWE Arena and the mode of Chat2Prototype.\n\n\u003ca href=\"https://swe-arena.com\"\u003e\u003cimg src=\"assets/demo.gif\"\u003e\u003c/a\u003e\n\n\n## About Us\n\nSWE Arena aims to establish transparent comparisons across different models while creating valuable datasets to advance research in code generation and App development. Our platform enables direct evaluation of LLM-generated programs, providing insights into model capabilities in software engineering tasks.\n\nWe welcome contributors to enhance the platform and encourage feedback to improve its functionality and usability.\n\n## Features\n\n#### Secure Code Execution\n- Sandboxed environment powered by E2B\n- Isolated runtime for each code execution\n- Resource usage monitoring and limitations\n- Secure dependency installation\n\n#### Dependency Management\n- Automatic dependency detection from imports\n- Support for both NPM and PIP package managers\n- Version specification and management\n- On-the-fly dependency modification\n\n#### Code Editing and Testing\n- Real-time code modification\n- Immediate execution feedback\n- Error handling and reporting\n- Support for multiple programming languages\n\n#### UI Interaction Tracking\n- Comprehensive logging of user interactions\n- Performance metrics collection\n- Usage analytics\n- Error tracking\n\n## Getting Started\n\n### Prerequisites\n1. Set up your E2B API Key:\n```bash\nexport E2B_API_KEY=\u003cYOUR_API_KEY\u003e\n```\n\n2. Set up other model API keys:\n```bash\nexport OPENAI_API_KEY=\u003cYOUR_API_KEY\u003e\nexport ANTHROPIC_API_KEY=\u003cYOUR_API_KEY\u003e\nexport GEMINI_API_KEY=\u003cYOUR_API_KEY\u003e\nexport QWEN_32B_API_KEY=\u003cYOUR_API_KEY\u003e\nexport QWEN_72B_API_KEY=\u003cYOUR_API_KEY\u003e\nexport QWEN_72B_INSTRUCT_API_KEY=\u003cYOUR_API_KEY\u003e\nexport HYPERBOLIC_API_KEY=\u003cYOUR_API_KEY\u003e\nexport DEEPSEEK_API_KEY=\u003cYOUR_API_KEY\u003e\n```\n\n3. Install dependencies:\n```bash\npip install -e \".[model_worker,webui]\"\n```\n\n### Running the Platform\n\n1. Start the server:\n```bash\n# text mode\npython -m fastchat.serve.gradio_web_server_multi --controller \"\" --register api_endpoints_serve.json\n\n# enable image mode\npython -m fastchat.serve.gradio_web_server_multi --controller \"\" --register api_endpoints_serve.json --vision-arena\n```\n\n2. Open your browser and navigate to `http://localhost:7860`\n\n## Contributing\n\nWe welcome contributions to enhance the platform! Here are some ways you can help:\n\n- Adding support for new programming languages\n- Enhancing UI/UX\n- Improving documentation\n- Reporting bugs and suggesting features\n\nSee [Sandbox Folder](fastchat/serve/sandbox) for more details about code execution.\n\n## Acknowledgements\n\nWe would like to thank the following projects for their contributions to SWE Arena:\n\n- [FastChat](https://github.com/lm-sys/FastChat)\n- [E2B](https://e2b.dev)\n- [Gradio](https://github.com/gradio-app/gradio)\n\n## License\n\nThis project is licensed under the Apache 2.0 License. See [LICENSE](LICENSE) for more details.\nAny data collected from SWE Arena and open-sourced will be under the Apache 2.0 License.\n\n## Citation\n\nIf you use SWE Arena in your research, please cite:\n\n```bibtex\n@misc{swe-arena2024,\n      title={SWE Arena: An Open Evaluation Platform for Automated Software Engineering},\n      year={2024}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FBigComputer-Project%2FSWE-Arena","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FBigComputer-Project%2FSWE-Arena","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FBigComputer-Project%2FSWE-Arena/lists"}