base on An self-improving embodied conversational agent seamlessly integrated into the operating system to automate our daily tasks. # OS-Copilot: Towards Generalist Computer Agents with Self-Improvement <div align="center"> <!-- [[PDF]](https://arxiv.org/pdf/2402.07456.pdf) [[Documentation]](https://os-copilot.readthedocs.io/en/latest/) --> [](https://os-copilot.github.io/) [](https://arxiv.org/pdf/2402.07456.pdf) [](https://os-copilot.readthedocs.io/en/latest/)  [](https://discord.com/invite/rXS2XbgfaD) [](https://twitter.com/oscopilot) <p align="center"> <img src='pic/demo.png' width="100%"> </p> </div> <!-- ## 📖 Overview - **OS-Copilot** is a pioneering conceptual framework for building generalist computer agents on Linux and MacOS, which provides a unified interface for app interactions in the heterogeneous OS ecosystem. <p align="center"> <img src='pic/framework.png' width="75%"> </p> - Leveraging OS-Copilot, we built **FRIDAY**, a self-improving AI assistant capable of solving general computer tasks. <p align="center"> <img src='pic/FRIDAY.png' width="75%"> </p> --> ## 🔥 News - _2024.9_: 🎉 Now Friday is equipped with vision! Try out the new [friday_vision](https://github.com/OS-Copilot/OS-Copilot/tree/main/examples/friday_vision)! Currently still under development but more stable versions are expected soon. - _2024.6_: 🎉 The front-end interface of OS-Copilot is now available. Go check it out in the [frontend](https://github.com/OS-Copilot/OS-Copilot/tree/main/fronted) directory! - _2024.3_: 🎉 OS-Copilot is accepted at the [LLM Agents Workshop](https://llmagents.github.io/)@ICLR 2024! ## What is OS-Copilot OS-Copilot is an open-source library to build generalist agents capable of automatically interfacing with comprehensive elements in an operating system (OS), including the web, code terminals, files, multimedia, and various third-party applications. ## ⚡️ Quickstart 1. **Clone the GitHub Repository:** ``` git clone https://github.com/OS-Copilot/OS-Copilot.git ``` 2. **Set Up Python Environment and Install Dependencies:** ``` conda create -n oscopilot_env python=3.10 -y conda activate oscopilot_env cd OS-Copilot pip install -e . ``` 3. **Set OpenAI API Key:** Configure your OpenAI API key in [.env](.env). ``` cp .env_template .env ``` 4. **Now you are ready to have fun:** ``` python quick_start.py ``` \* **FRIDAY currently only supports single-round conversation**. ## 🛠️ Tutorial | **Level** | **Tutorial** | **Description** | | ---------------- | ----------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------ | | **Beginner** | [Installation](https://os-copilot.readthedocs.io/en/latest/installation.html) | Explore three methods to install FRIDAY. | | **Beginner** | [Getting Started](https://os-copilot.readthedocs.io/en/latest/quick_start.html) | The simplest demonstration of FRIDAY with a quick_start.py script. | | **Intermediate** | [Adding Your Tools](https://os-copilot.readthedocs.io/en/latest/tutorials/add_tool.html) | Adding and removing tools to the FRIDAY. | | **Intermediate** | [Deploying API Services](https://os-copilot.readthedocs.io/en/latest/tutorials/deploy_api_service.html) | Demonstrate the deployment of API services for FRIDAY. | | **Intermediate** | [Example: Automating Excel Tasks](https://os-copilot.readthedocs.io/en/latest/tutorials/example_excel.html) | Automating Excel control using FRIDAY. | | **Intermediate** | [Enhancing FRIDAY with Self-Learning for Excel Task Automation](https://os-copilot.readthedocs.io/en/latest/tutorials/self_learning.html) | Improved Excel control with self-directed learning. | | **Advanced** | [Designing New API Tools](https://os-copilot.readthedocs.io/en/latest/tutorials/design_new_api_tool.html) | Guides on deploying custom API tools for FRIDAY to extend its functionalities. | <!-- ## 🛠️ FRIDAY-Gizmos We maintain an open-source library of toolkits for FRIDAY, which includes tools that can be directly utilized within FRIDAY. For a detailed list of tools, please see [FRIDAY-Gizmos](https://github.com/OS-Copilot/FRIDAY-Gizmos). The usage methods are as follows: 1. Find the tool you want to use in [FRIDAY-Gizmos](https://github.com/OS-Copilot/FRIDAY-Gizmos) and download its tool code. 2. Add the tool to FRIDAY's toolkit: ```shell python friday/tool_repository/manager/tool_manager.py --add --tool_name [tool_name] --tool_path [tool_path] ``` 3. If you wish to remove a tool, you can run: ```shell python friday/tool_repository/manager/tool_manager.py --delete --tool_name [tool_name] ``` ## 💻 User Interface (UI) **Enhance Your Experience with Our Intuitive Frontend!** This interface is crafted for effortless control of your agents. For more details, visit [FRIDAY Frontend](https://github.com/OS-Copilot/FRIDAY-front). ## ✨ Deploy API Services For comprehensive guidelines on deploying API services, please refer to the [OS-Copilot documentation](https://os-copilot.readthedocs.io/en/latest/). --> ## 💻 User Interface (UI) **Enhance Your Experience with Our Intuitive Frontend!** This interface is crafted for effortless control of your agents. For more details, visit [OS-Copilot Frontend](https://github.com/OS-Copilot/OS-Copilot/tree/main/fronted). ## 🏫 Community Join our community to connect with other enthusiasts, researchers and developers: - **[Discord](https://discord.com/invite/rXS2XbgfaD)**: Join our Discord server for real-time discussions and support. - **[Twitter](https://twitter.com/oscopilot)**: Follow our Twitter to get latest new or tag us to share your demos! ## 👨‍💻‍ Contributing **Visit [the roadmap](./docs/roadmap.md) to preview what the community is working on and become a contributor!** <a href="https://github.com/OS-Copilot/OS-Copilot/graphs/contributors"> <img src="https://contrib.rocks/image?repo=OS-Copilot/OS-Copilot" /> </a> <!-- Made with [contrib.rocks](https://contrib.rocks). --> ## 🛡 Disclaimer OS-Copilot is provided "as is" without warranty of any kind. Users assume full responsibility for any risks associated with its use, including **potential data loss** or **changes to system settings**. The developers of OS-Copilot are not liable for any damages or losses resulting from its use. Users must ensure their actions comply with applicable laws and regulations. ## 🔎 Citation ``` @article{wu2024copilot, title={Os-copilot: Towards generalist computer agents with self-improvement}, author={Wu, Zhiyong and Han, Chengcheng and Ding, Zichen and Weng, Zhenmin and Liu, Zhoumianze and Yao, Shunyu and Yu, Tao and Kong, Lingpeng}, journal={arXiv preprint arXiv:2402.07456}, year={2024} } ``` ## 📬 Contact If you have any inquiries, suggestions, or wish to contact us for any reason, we warmly invite you to email us at [email protected]. ## Star History  ", Assign "at most 3 tags" to the expected json: {"id":"10118","tags":[]} "only from the tags list I provide: [{"id":77,"name":"3d"},{"id":89,"name":"agent"},{"id":17,"name":"ai"},{"id":54,"name":"algorithm"},{"id":24,"name":"api"},{"id":44,"name":"authentication"},{"id":3,"name":"aws"},{"id":27,"name":"backend"},{"id":60,"name":"benchmark"},{"id":72,"name":"best-practices"},{"id":39,"name":"bitcoin"},{"id":37,"name":"blockchain"},{"id":1,"name":"blog"},{"id":45,"name":"bundler"},{"id":58,"name":"cache"},{"id":21,"name":"chat"},{"id":49,"name":"cicd"},{"id":4,"name":"cli"},{"id":64,"name":"cloud-native"},{"id":48,"name":"cms"},{"id":61,"name":"compiler"},{"id":68,"name":"containerization"},{"id":92,"name":"crm"},{"id":34,"name":"data"},{"id":47,"name":"database"},{"id":8,"name":"declarative-gui "},{"id":9,"name":"deploy-tool"},{"id":53,"name":"desktop-app"},{"id":6,"name":"dev-exp-lib"},{"id":59,"name":"dev-tool"},{"id":13,"name":"ecommerce"},{"id":26,"name":"editor"},{"id":66,"name":"emulator"},{"id":62,"name":"filesystem"},{"id":80,"name":"finance"},{"id":15,"name":"firmware"},{"id":73,"name":"for-fun"},{"id":2,"name":"framework"},{"id":11,"name":"frontend"},{"id":22,"name":"game"},{"id":81,"name":"game-engine "},{"id":23,"name":"graphql"},{"id":84,"name":"gui"},{"id":91,"name":"http"},{"id":5,"name":"http-client"},{"id":51,"name":"iac"},{"id":30,"name":"ide"},{"id":78,"name":"iot"},{"id":40,"name":"json"},{"id":83,"name":"julian"},{"id":38,"name":"k8s"},{"id":31,"name":"language"},{"id":10,"name":"learning-resource"},{"id":33,"name":"lib"},{"id":41,"name":"linter"},{"id":28,"name":"lms"},{"id":16,"name":"logging"},{"id":76,"name":"low-code"},{"id":90,"name":"message-queue"},{"id":42,"name":"mobile-app"},{"id":18,"name":"monitoring"},{"id":36,"name":"networking"},{"id":7,"name":"node-version"},{"id":55,"name":"nosql"},{"id":57,"name":"observability"},{"id":46,"name":"orm"},{"id":52,"name":"os"},{"id":14,"name":"parser"},{"id":74,"name":"react"},{"id":82,"name":"real-time"},{"id":56,"name":"robot"},{"id":65,"name":"runtime"},{"id":32,"name":"sdk"},{"id":71,"name":"search"},{"id":63,"name":"secrets"},{"id":25,"name":"security"},{"id":85,"name":"server"},{"id":86,"name":"serverless"},{"id":70,"name":"storage"},{"id":75,"name":"system-design"},{"id":79,"name":"terminal"},{"id":29,"name":"testing"},{"id":12,"name":"ui"},{"id":50,"name":"ux"},{"id":88,"name":"video"},{"id":20,"name":"web-app"},{"id":35,"name":"web-server"},{"id":43,"name":"webassembly"},{"id":69,"name":"workflow"},{"id":87,"name":"yaml"}]" returns me the "expected json"