Project Info
This project did not submit a demo video on Devpost.
Inspiration
In the rapidly evolving world of blockchain and cryptocurrency, many users find themselves overwhelmed by the complexity of managing digital assets. We were inspired to create Bull Rider after observing the steep learning curve faced by newcomers to the Sui blockchain ecosystem. Our goal was to develop an intuitive, voice-controlled assistant that simplifies blockchain interactions and makes cryptocurrency management accessible to everyone. What It Does Bull Rider is an innovative voice-controlled assistant designed to simplify interactions with the Sui blockchain. Key features include: Voice-activated tutorials: Users can ask questions about Sui wallet operations, and Bull Rider provides step-by-step audio guidance, complemented by on-screen instructions. Voice-controlled transactions: Users can initiate cryptocurrency transfers using natural language commands, making sending tokens as easy as speaking to a friend. Context-aware assistance: Bull Rider uses RAG (Retrieval-Augmented Generation) to provide accurate, up-to-date information about Sui wallet operations. Dynamic tutorial generation: The assistant analyzes the user's screen and query to create personalized, context-specific tutorials. Seamless integration: Bull Rider operates as a menu bar application, always ready to assist without interrupting the user's workflow. How We Built It Bull Rider is built using a combination of cutting-edge technologies: Frontend: Python with rumps for the macOS menu bar interface. Backend: FastAPI for the REST API. Natural Language Processing: Groq API for parsing voice commands and generating responses. Speech-to-Text and Text-to-Speech: Deepgram API for accurate transcription and natural-sounding speech synthesis. Image Analysis: Hyperbolic API for screen capture analysis and tutorial generation. Database: SQLite for lightweight, serverless data storage. RAG System: Sentence Transformers and FAISS for efficient information retrieval. Blockchain Integration: Custom Sui blockchain client for executing transactions. Challenges We Ran Into Integrating multiple AI services (Groq, Deepgram, Hyperbolic) seamlessly. Implementing an efficient RAG system for context-aware responses. Ensuring accurate voice command parsing for blockchain transactions. Optimizing the tutorial generation process for real-time responsiveness. Balancing between providing detailed guidance and maintaining simplicity in user interactions. Accomplishments That We're Proud Of Creating a voice-controlled assistant that simplifies complex blockchain operations. Successfully implementing a RAG system for providing accurate, context-aware information. Developing a dynamic tutorial generation system that adapts to the user's screen and query. Integrating multiple AI services to create a seamless, intelligent user experience. Building a non-intrusive, always-available assistant as a menu bar application. What We Learned The importance of context in AI-generated responses for blockchain applications. Techniques for efficient information retrieval and embedding in RAG systems. Strategies for integrating multiple AI services into a cohesive application. The complexities of voice-controlled interfaces for financial transactions. The potential of AI to simplify complex technological interactions. What's Next for Bull Rider Expanding support for multiple blockchain ecosystems beyond Sui. Implementing more advanced voice authentication for enhanced security. Developing a mobile version of the assistant for on-the-go blockchain management. Integrating real-time market data and portfolio management features. Collaborating with blockchain projects to provide tailored assistance for specific dApps and services. Implementing a feedback loop to continuously improve the RAG system and tutorial generation. Bull Rider represents a significant step towards making blockchain technology accessible to everyone. By combining voice control, AI-driven assistance, and intuitive design, we're paving the way for wider adoption of cryptocurrency and decentralized technologies.
Bull Rider
Inspiration
In the rapidly evolving world of blockchain and cryptocurrency, many users find themselves overwhelmed by the complexity of managing digital assets. We were inspired to create Bull Rider after observing the steep learning curve faced by newcomers to the Sui blockchain ecosystem. Our goal was to develop an intuitive, voice-controlled assistant that simplifies blockchain interactions and makes cryptocurrency management accessible to everyone.
What It Does
Bull Rider is an innovative voice-controlled assistant designed to simplify interactions with the Sui blockchain. Key features include:
- Voice-activated tutorials: Users can ask questions about Sui wallet operations, and Bull Rider provides step-by-step audio guidance, complemented by on-screen instructions.
- Voice-controlled transactions: Users can initiate cryptocurrency transfers using natural language commands, making sending tokens as easy as speaking to a friend.
- Context-aware assistance: Bull Rider uses RAG (Retrieval-Augmented Generation) to provide accurate, up-to-date information about Sui wallet operations.
- Dynamic tutorial generation: The assistant analyzes the user's screen and query to create personalized, context-specific tutorials.
- Seamless integration: Bull Rider operates as a menu bar application, always ready to assist without interrupting the user's workflow.
How We Built It
Bull Rider is built using a combination of cutting-edge technologies:
- Frontend: Python with rumps for the macOS menu bar interface.
- Backend: FastAPI for the REST API.
- Natural Language Processing: Groq API for parsing voice commands and generating responses.
- Speech-to-Text and Text-to-Speech: Deepgram API for accurate transcription and natural-sounding speech synthesis.
- Image Analysis: Hyperbolic API for screen capture analysis and tutorial generation.
- Database: SQLite for lightweight, serverless data storage.
- RAG System: Sentence Transformers and FAISS for efficient information retrieval.
- Blockchain Integration: Custom Sui blockchain client for executing transactions.
Challenges We Ran Into
- Integrating multiple AI services (Groq, Deepgram, Hyperbolic) seamlessly.
- Implementing an efficient RAG system for context-aware responses.
- Ensuring accurate voice command parsing for blockchain transactions.
- Optimizing the tutorial generation process for real-time responsiveness.
- Balancing between providing detailed guidance and maintaining simplicity in user interactions.
Accomplishments That We're Proud Of
- Creating a voice-controlled assistant that simplifies complex blockchain operations.
- Successfully implementing a RAG system for providing accurate, context-aware information.
- Developing a dynamic tutorial generation system that adapts to the user's screen and query.
- Integrating multiple AI services to create a seamless, intelligent user experience.
- Building a non-intrusive, always-available assistant as a menu bar application.
What We Learned
- The importance of context in AI-generated responses for blockchain applications.
- Techniques for efficient information retrieval and embedding in RAG systems.
- Strategies for integrating multiple AI services into a cohesive application.
- The complexities of voice-controlled interfaces for financial transactions.
- The potential of AI to simplify complex technological interactions.
What's Next for Bull Rider
- Expanding support for multiple blockchain ecosystems beyond Sui.
- Implementing more advanced voice authentication for enhanced security.
- Developing a mobile version of the assistant for on-the-go blockchain management.
- Integrating real-time market data and portfolio management features.
- Collaborating with blockchain projects to provide tailored assistance for specific dApps and services.
- Implementing a feedback loop to continuously improve the RAG system and tutorial generation.
Bull Rider represents a significant step towards making blockchain technology accessible to everyone. By combining voice control, AI-driven assistance, and intuitive design, we're paving the way for wider adoption of cryptocurrency and decentralized technologies.
Analysis
View
Metric
- 23
- 15
- 8
- 4
Figures cover GitHub contributors during the hackathon window. A co-authored commit counts in full for each author, so per-member totals add up to more than the whole-team figures.
Technology
- CSSIn code
- FastAPIIn code
- HTMLIn code
- Hugging FaceIn code
- JavaScriptIn code
- PythonIn code
- PyTorchIn code
- ReactIn code
- Tailwind CSSIn code
9 of 9 appear in the indexed code.
AI coding agents
No AI coding agent signals were found in this repository.
Detected from committed agent config files and commit authorship. Absence of a signal is not proof an agent was unused.
Codebase size
Source size
74 KB
Source files
41
Counts recognized source files only; vendored directories, binaries and lockfiles are excluded, so this is smaller than the repository on disk.
Repository
tusharg0101/bull_rider
60 files · 1.3 MB · @ cd108a6
Structure
Interface
13 files · 22%Screens, components and styles rendered to the user.
Application logic
25 files · 42%Domain rules, services and shared utilities.
Supporting
Layers are inferred from where files sit in the tree, not from reading the code. A project that names its directories unconventionally will read oddly here — open the file browser to check anything the diagram implies.
Languages
- Python53%
- JavaScript29%
- Markdown10%
- CSS7%
- HTML1%
Share of indexed source by file size. Binary and vendored files are excluded.
Dependencies
requirements.txt
pypi · 108- aenum
- aiofiles
- aiohappyeyeballs
- aiohttp
- aiomysql
- aiosignal
- aiosqlite
- annotated-types
- anyio
- astroid
- attrs
- beautifulsoup4
- bs4
- certifi
- charset-normalizer
- click
- dataclasses-json
- deepgram-sdk
- +90 more
backend/requirements.txt
pypi · 78- aenum
- aiofiles
- aiohappyeyeballs
- aiohttp
- aiomysql
- aiosignal
- aiosqlite
- annotated-types
- anyio
- attrs
- certifi
- charset-normalizer
- click
- dataclasses-json
- deepgram-sdk
- deprecation
- distro
- dnspython
- +60 more
frontend/br-nlp-web_app/package.json
npm · 15- @testing-library/jest-dom
- @testing-library/react
- @testing-library/user-event
- axios
- mic-recorder-to-mp3
- react
- react-dom
- react-router-dom
- react-scripts
- reconnecting-websocket
- recordrtc
- web-vitals
- +3 more
Declared in the repository’s manifests at the indexed commit. A declared package is not proof it is used, and runtime dependencies are listed first.
This project’s features have not been analysed yet.
Export this project's context (description, README, evidence, key source files) to chat with an AI agent elsewhere.