HAI Code Generator is a cutting-edge tool designed to simplify and automate task execution while enhancing code generation workflows. Leveraging Specif AI, it streamlines processes like task execution, file identification, and code documentation through intelligent automation and AI-driven capabilities.
ποΈ Built on Cline's powerful foundation for AI-assisted development.
- π§βπ» Experts : Context-aware code generation with built-in and custom domain experts
- βοΈ Inline Editing : Make quick, AI-assisted edits without leaving your codebase
- π HAI Tasks : Integrate AI-generated user stories and tasks seamlessly into your workflow
- π File Identification : Discover and contextualize code files with intelligent indexing
- βοΈ Settings Interface : Easily configure LLMs and embedding models for tailored performance
- π COR-Matrix Integration : Track AI code retention patterns and analyze code origin over time
- π Overview
- π₯ Getting Started
- β¨ Features
- π€ Contributing
- π License
- π Acknowledgments
- π§ Contact
HAI Code Generator is designed to boost productivity and precision by automating task execution and integrating file management capabilities. It combines intelligent file indexing, context generation, and LLM-driven automation to minimize manual effort and ensure task accuracy. With user-friendly interfaces and configurable settings, HAI Code Generator is perfect for both developers and teams aiming to enhance their workflows.
- Open Visual Studio Code β Extensions (β§βX) β Search for βHAI Buildβ β Click Install
- Upon installation, the HAI extension can be found in the sidebar.
Harness the power of AI for seamless task management and user-story execution, HAI Code Generator integrates tasks generated by Specif AI, allowing them to be loaded directly into the HAI Tasks page. This streamlined process enables you to:
- Review AI-generated tasks within a dedicated interface.
- Execute them instantly with a single click.
- Manage all tasks in one place for improved clarity and productivity.
By centralizing AI-driven tasks in HAI Code Generator, you can maintain an efficient workflow from ideation to execution.
-
In-Depth Story Review
- View a story in detail by clicking the Eye icon, along with the corresponding list of tasks, providing comprehensive insights into objectives, prerequisites, and outcomes.
-
In-Depth Task Review
- Similar to user stories, tasks can be viewed in detail and executed directly from the same interface.
Configure external telemetry settings to monitor and analyze your AI-powered development workflows with environment-specific customization capabilities.
-
External Configuration Override
- Support for telemetry configuration overrides via a
.hai.configfile placed at the root of your workspace. - Enables environment-specific customization that can be dynamically injected through CI/CD pipelines.
- Support for telemetry configuration overrides via a
-
Supported Override Parameters
# Langfuse Configuration langfuse.apiUrl= langfuse.apiKey= langfuse.publicKey= # PostHog Configuration posthog.url= posthog.apiKey=
Important Notes:
- The
.hai.configfile is not git-excluded by default. Ensure sensitive keys are not committed unintentionally to your repository.
The Experts feature enables HAI Code Generator to deliver context-aware code generation tailored to specific technologies or domains.
- Four built-in experts are available: .NET, Terraform, Node.js, and Go.
- Each provides predefined guidelines and best practices in read-only mode for quick reference.
- Users can create custom experts to define their own guidelines and (optionally) attach up to three reference document links.
- Custom experts are stored in the
.hai-expertsfolder under a subfolder named after the expert. - Each expert folder contains:
metadata.json: Stores expert name, creation date, and any document links.prompt.md: Contains the expertβs guidelines (required).
- If document links are provided, a
docsfolder is created with:- Markdown files for each processed document.
status.jsonto track processing status.
Note:
- Expert name and guidelines are mandatory when creating a custom expert.
- Document links are optional and can be added for richer context.
This feature allows you to extend HAI Code Generatorβs knowledge with your own standards, best practices, and documentationβensuring more accurate and relevant code generation for your unique stack.
For comprehensive documentation and in-depth guides on HAI Code Generator features, visit our Wiki.
To contribute to the project, start by exploring open issues or checking our feature request board.
To get started with HAI Code Generator, follow these steps:
Local Development Instructions
-
Clone the repository (Requires git-lfs):
git clone https://github.com/presidio-oss/hai-build-codegen
-
Open the project in VSCode:
code hai-build-codegen
-
Install the necessary dependencies for the extension and webview-gui:
npm run install:all
-
Launch by pressing F5 (or Run -> Start Debugging) to open a new VSCode window with the extension loaded. (You may need to install the esbuild problem matchers extension if you run into issues building the project.)
Please read our Contributing Guidelines for more details.
This project is licensed under the Apache 2.0 License. See the LICENSE file for more details.
Thanks to all contributors and users for their support and feedback.
For any questions or feedback, please contact us at hai-feedback@presidio.com.




