Rubra

What is Rubra?

Rubra is an open-source platform designed for building local AI assistants. It provides a cost-effective solution that allows developers to create AI-powered applications without the need for API tokens. Rubra offers several benefits such as working locally, saving tokens, and ensuring data privacy by running all processes on the user's local machine. It integrates a user-friendly chat UI for efficient interaction with models and supports multi-channel data processing. Compared to OpenAI's ChatGPT, Rubra stands out for its local development focus, privacy emphasis, integrated LLMs, and flexibility between local and cloud development.

Rubra includes various pretrained AI models optimized for local development, such as Mistral-7B, Phi-3-mini-128k, and Qwen2-7B. These models are enhanced from top open-source LLMs and enable developers to interact with them locally. Rubra also supports the integration of OpenAI and Anthropic models, allowing developers to choose between different AI models based on their specific needs.

Additionally, Rubra's user-friendly chat interface enables effective communication with AI assistants and models. It offers an API that is compatible with OpenAI's Assistants API, facilitating seamless transitions between local and cloud development environments. Rubra's privacy-focused design ensures that all processes remain on the user's local machine, safeguarding chat histories and data privacy.

Furthermore, Rubra allows contributions and feedback from the community through its GitHub repository, welcoming bug reports and code submissions to enhance the tool's capabilities. By providing a platform for local testing of AI assistants, developers can evaluate performance within a realistic setting while maintaining privacy and data security.

Who created Rubra?

Rubra was created by the Rubra team. It was launched on February 14, 2024, as an open-source platform for building local AI assistants. The platform was founded to enable developers to create AI-powered applications in a cost-effective and private manner, eliminating the need for API tokens. Rubra's focus is on enabling the development of AI assistants powered by locally running, open-source large language models (LLMs).

What is Rubra used for?

• Ensuring data privacy
• Building local AI assistants
• Creating AI-powered applications
• Working in a cost-effective and private manner
• Comparing assistant performance across different models
• Calling user-defined external tools in a deterministic manner
• Ideal for agentic use cases
• Enhancing open-weight large language models with tool-calling capability
• Mitigating catastrophic forgetting in models
• Running Rubra models locally
• Contributing to Rubra's development
• Creating AI-powered applications in a cost-effective and private manner without the need for API tokens
• Working locally to save tokens and ensure data privacy
• Accessing built-in open-source Large Language Models (LLMs)
• Bypassing the need for tokens during API calls
• Focusing on the development of AI assistants
• Interchanging between local and cloud development
• Calling user-defined external tools in a deterministic manner while reasoning and chatting
• Enhancing top open-weight large language models with tool-calling capability
• Interacting with models locally
• Enhancing large language models with tool-calling capability
• Facilitating agentic use cases
• Running Rubra models easily
• Creating AI-powered applications in a cost-effective manner
• Working locally without API tokens
• Accessing built-in open-source LLMs
• Calling user-defined external tools

Who is Rubra for?

• Developers
• AI-powered application creators
• AI Application Creators
• AI developers
• Assistants developers
• AI Programmers
• Chatbot developers
• AI researchers
• Application Developers
• AI Assistants

How to use Rubra?

To use Rubra, follow these steps:

1. Begin by installing Rubra with a simple one-command installation using: curl -sfL https://get.rubra.ai | sh -s -- start.

2. Create and tweak AI assistant models using the fully integrated Large Language Model (LLM), specifically based on the Mistral model.

3. Interact with models locally via the user-friendly chat interface provided by Rubra.

4. Utilize the API compatible with OpenAI's Assistants API to easily transition between local and cloud development.

5. Ensure data privacy as all processes run locally on your machine, safeguarding chat histories and preventing data transfer to external servers.

6. Access pre-configured open-source LLMs, including Mistral-based models, and the ability to integrate other models like those from OpenAI and Anthropic.

7. Test AI assistants locally, evaluating their performance under real-world conditions without leaving the safety of your own machine.

8. Explore the documentation available on the Rubra website for additional guidance and details on features, installation, and more.

9. For assistance and issue resolution, engage with the Rubra community via GitHub or the Discord channel.

These steps will help you effectively leverage Rubra's capabilities for developing AI-powered applications locally with privacy, cost-effectiveness, and efficiency.