{"id":13682317,"url":"https://github.com/huangd1999/AgentCoder","last_synced_at":"2025-04-30T09:31:56.279Z","repository":{"id":230916791,"uuid":"774779660","full_name":"huangd1999/AgentCoder","owner":"huangd1999","description":"This Repo is the official implementation of AgentCoder and AgentCoder+.","archived":false,"fork":false,"pushed_at":"2024-08-10T07:05:00.000Z","size":889,"stargazers_count":155,"open_issues_count":5,"forks_count":30,"subscribers_count":2,"default_branch":"main","last_synced_at":"2024-08-10T08:24:25.136Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/huangd1999.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2024-03-20T07:02:44.000Z","updated_at":"2024-08-10T07:05:04.000Z","dependencies_parsed_at":"2024-04-01T15:49:37.114Z","dependency_job_id":"cdcab579-8bbf-447a-8a24-22134134addb","html_url":"https://github.com/huangd1999/AgentCoder","commit_stats":null,"previous_names":["huangd1999/agentcoder"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/huangd1999%2FAgentCoder","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/huangd1999%2FAgentCoder/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/huangd1999%2FAgentCoder/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/huangd1999%2FAgentCoder/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/huangd1999","download_url":"https://codeload.github.com/huangd1999/AgentCoder/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":224206004,"owners_count":17273376,"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":"2024-08-02T13:01:44.088Z","updated_at":"2025-04-30T09:31:56.273Z","avatar_url":"https://github.com/huangd1999.png","language":"Python","readme":"# AgentCoder: Multiagent-Code Generation Framework\n\nAgentCoder is a novel multiagent-code generation framework that leverages the power of large language models (LLMs) to enhance the effectiveness of code generation. The framework consists of three specialized agents: the programmer agent, the test designer agent, and the test executor agent. These agents collaborate to generate high-quality code snippets, design comprehensive test cases, and ensure the correctness of the generated code through an iterative feedback loop.\n\n## Key Features\n\n- **Multiagent Collaboration**: AgentCoder utilizes a multiagent framework where each agent specializes in a specific task, leading to improved code generation effectiveness.\n- **Independent Test Case Generation**: The test designer agent generates diverse and objective test cases independently, ensuring comprehensive testing of the generated code.\n- **Iterative Code Refinement**: The test executor agent executes the generated test cases against the code and provides feedback to the programmer agent for iterative code refinement.\n- **Modularity and Scalability**: The modular structure of AgentCoder allows for easy integration with advanced models and future enhancements, ensuring adaptability in the evolving landscape of code generation.\n\n## Installation\n\nTo use AgentCoder, you need to have an API key from OpenAI or other similar third-party providers.\n1. Clone the AgentCoder repository:\n   ```\n   git clone https://github.com/your-username/AgentCoder.git\n   cd AgentCoder\n   git clone https://github.com/THUDM/CodeGeeX\n   ```\n\n2. Install the required dependencies:\n   ```\n   pip install -r requirements.txt\n   ```\n\n3. Add your API key in the `.env` file:\n   ```python\n   OPENAI_API_KEY=\"YOUR_OPENAI_API_KEY\"\n   ```\n\n## Usage\n\n### Code Generation\n\nTo generate code snippets, run the following commands:\n```\npython programmer_[humaneval/mbpp].py\n```\nThese scripts will generate code snippets that will be used for test case generation.\n\n### Test Case Generation\n\nTo generate test cases, run the following command:\n```\npython test_designer_[humaneval/mbpp].py\n```\nThis script will generate diverse and comprehensive test cases based on the coding requirements.\n\n### Self-Optimization Process\n\nTo perform the self-optimization process, run the following commands:\n```\npython test_executor_[humaneval/mbpp].py\n```\nThese scripts will execute the generated test cases against the code and provide feedback to the programmer agent for iterative code refinement.\n\n\n## Contributions\n\nContributions to AgentCoder are welcome! If you find any issues or have suggestions for improvements, please open an issue or submit a pull request on the GitHub repository.\n\n## License\n\nAgentCoder is released under the [MIT License](LICENSE).\n\n## Acknowledgments\n\nWe would like to thank AIOHUB for providing funding and support for the development of AgentCoder. We also acknowledge the contributions of the open-source community and the developers of the large language models used in this project.\n","funding_links":[],"categories":["Python","A01_文本生成_文本对话"],"sub_categories":["大语言对话模型及数据"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhuangd1999%2FAgentCoder","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhuangd1999%2FAgentCoder","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhuangd1999%2FAgentCoder/lists"}