{"id":28834624,"url":"https://github.com/yym68686/aient","last_synced_at":"2026-03-14T22:11:29.199Z","repository":{"id":238811135,"uuid":"797631795","full_name":"yym68686/aient","owner":"yym68686","description":"Aient: The Awakening of Agent.","archived":false,"fork":false,"pushed_at":"2026-01-12T14:59:21.000Z","size":354,"stargazers_count":38,"open_issues_count":0,"forks_count":13,"subscribers_count":2,"default_branch":"main","last_synced_at":"2026-01-12T21:29:17.488Z","etag":null,"topics":["agent","claude","dalle-3","duckduckgo","gemini","gpt-4","groq"],"latest_commit_sha":null,"homepage":"","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/yym68686.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,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2024-05-08T08:06:07.000Z","updated_at":"2026-01-12T14:59:25.000Z","dependencies_parsed_at":"2024-06-24T18:24:00.428Z","dependency_job_id":"a9e4d80d-39bd-48f4-bab3-eaac3ab4808c","html_url":"https://github.com/yym68686/aient","commit_stats":null,"previous_names":["yym68686/llm-hub","yym68686/modelmerge","yym68686/aient"],"tags_count":7,"template":false,"template_full_name":null,"purl":"pkg:github/yym68686/aient","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yym68686%2Faient","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yym68686%2Faient/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yym68686%2Faient/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yym68686%2Faient/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/yym68686","download_url":"https://codeload.github.com/yym68686/aient/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yym68686%2Faient/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30519320,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-14T19:51:21.629Z","status":"ssl_error","status_checked_at":"2026-03-14T19:51:12.959Z","response_time":57,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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","claude","dalle-3","duckduckgo","gemini","gpt-4","groq"],"created_at":"2025-06-19T09:41:28.175Z","updated_at":"2026-03-14T22:11:29.193Z","avatar_url":"https://github.com/yym68686.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# aient\n\n[English](./README.md) | [Chinese](./README_CN.md)\n\naient is a powerful library designed to simplify and unify the use of different large language models, including gpt-4.1/5, o3, DALL-E 3, claude4, gemini-2.5-pro/flash, Vertex AI (Claude, Gemini), and Groq. The library supports GPT format function calls and has built-in Google search and URL summarization features, greatly enhancing the practicality and flexibility of the models.\n\n## ✨ Features\n\n- **Multi-model support**: Integrate various latest large language models.\n- **Real-time Interaction**: Supports real-time query streams, real-time model response retrieval.\n- **Function Expansion**: With built-in function calling support, the model's functions can be easily expanded, currently supporting plugins such as DuckDuckGo and Google search, content summarization, Dalle-3 drawing, arXiv paper summaries, current time, code interpreter, and more.\n- **Simple Interface**: Provides a concise and unified API interface, making it easy to call and manage the model.\n\n## Quick Start\n\nThe following is a guide on how to quickly integrate and use aient in your Python project.\n\n### Install\n\nFirst, you need to install aient. It can be installed directly via pip:\n\n```bash\npip install aient\n```\n\n### Usage example\n\nThe following is a simple example demonstrating how to use aient to request the GPT-4 model and handle the returned streaming data:\n\n```python\nfrom aient import chatgpt\n\n# Initialize the model, set the API key and the selected model\nbot = chatgpt(api_key=\"{YOUR_API_KEY}\", engine=\"gpt-4o\")\n\n# Get response\nresult = bot.ask(\"python list use\")\n\n# Send request and get streaming response in real-time\nfor text in bot.ask_stream(\"python list use\"):\n    print(text, end=\"\")\n\n# Disable all plugins\nbot = chatgpt(api_key=\"{YOUR_API_KEY}\", engine=\"gpt-4o\", use_plugins=False)\n```\n\n## 🍃 Environment Variables\n\nThe following is a list of environment variables related to plugin settings:\n\n| Variable Name | Description | Required? |\n|---------------|-------------|-----------|\n| get_search_results | Enable search plugin. Default value is `False`. | No |\n| get_url_content | Enable URL summary plugin. The default value is `False`. | No |\n| download_read_arxiv_pdf | Whether to enable the arXiv paper abstract plugin. The default value is `False`. | No |\n| run_python_script | Whether to enable the code interpreter plugin. The default value is `False`. | No |\n| generate_image | Whether to enable the image generation plugin. The default value is `False`. | No |\n| get_time | Whether to enable the date plugin. The default value is `False`. | No |\n\n## Supported models\n\n- gpt-4.1/5\n- o3\n- DALL-E 3\n- claude4\n- gemini-2.5-pro/flash\n- Vertex AI (Claude, Gemini)\n- Groq\n\n## 🧩 Plugin\n\nThis project supports multiple plugins, including: DuckDuckGo and Google search, URL summary, ArXiv paper summary, DALLE-3 drawing, and code interpreter, etc. You can enable or disable these plugins by setting environment variables.\n\n- How to develop a plugin?\n\nThe plugin-related code is all in the aient git submodule of this repository. aient is an independent repository I developed for handling API requests, conversation history management, and other functionality. When you clone this repository with the `--recurse-submodules` parameter, aient will be automatically downloaded. All plugin code is located in the relative path `aient/src/aient/plugins` in this repository. You can add your own plugin code in this directory. The plugin development process is as follows:\n\n1. Create a new Python file in the `aient/src/aient/plugins` directory, for example, `myplugin.py`. Register the plugin by adding the `@register_tool()` decorator above the function. Import `register_tool` with `from .registry import register_tool`.\n\nAfter completing the above steps, your plugin is ready to use. 🎉\n\n## License\n\nThis project is licensed under the MIT License.\n\n## Contribution\n\nWelcome to contribute improvements by submitting issues or pull requests through GitHub.\n\n## Contact Information\n\nIf you have any questions or need assistance, please contact us at [yym68686@outlook.com](mailto:yym68686@outlook.com).","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyym68686%2Faient","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fyym68686%2Faient","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyym68686%2Faient/lists"}