cortesh is a LLM based CLI tool that interacts with your coding project. It aims to:
- 🚀 Quickly bootstrap new software projects.
- 📂 Generate embeddings and/or custom trainings for your existing projects.
- 📑 Implement features and functionalities.
- ⚡ Create and run tests.
- 🐞Debug and fix bugs.
- 🔒Automatic security and performance analysis.
- Initialize with OpenAI.
- [ Logic ] - folder_project - entry point to handle user requests on a folder project.
- [ Output ] Write files and run commands from LLM answers.
- [ Logic ] Feedback loop for command outputs. Flow control.
- [ Sense ] Read current files and project structure, flow control by LLM.
- [ Memory ] Generate embeddings on curent project structure, include GIT/LLM generated descriptions.
- [ Logic ] Use the memory embedidngs in flow control
- [ Memory ] Indexing parallel requests.
- [ FlowControl ] Refactor sense/output, to be generic among knowledge/folder_structure, or any other command.
- [ Sense ] Memory as a sense tool.
- Some kind of testing...
pip install corteshFor an existing project, it's recommended that you first index your poject knowledge:
cortesh --indexThis will generate a configuration file and store the embeddings in .cortesh folder.
Go to the folder where you want to start working and run:
corteshTo be able to fully implement a feature on a public repository in a completely autonomous way.
- Code Generation with AlphaCodium
- Many-Shot In-Context learning
- Chain of Agents: Large Language Models Collaborating on Long-Context Tasks
We welcome contributions! Here's how you can help:
- Fork the repository 🍴
- Create your feature branch (
git checkout -b feature/your-feature) 🌱 - Commit your changes (
git commit -am 'Add some feature') 💡 - Push to the branch (
git push origin feature/your-feature) 🚀 - Open a Pull Request ✨
Check the Contributing Guidelines for more information.
This project is licensed under the MIT License. See the LICENSE file for details.
Happy Coding! ✨