BlockAGI is an open-source research agent built with Python3, utilizing the capabilities of LangChain and OpenAI. It conducts iterative, domain-specific research, primarily focused on cryptocurrency but customizable to other domains. This blog post introduces BlockAGI and highlights its features, tech stack, and installation process.
BlockAGI is an AI-powered research agent designed to assist users in conducting research on various topics, with a primary focus on cryptocurrency. It leverages the power of LangChain and OpenAI to gather, refine, and evaluate information, and generates detailed narrative reports to showcase its findings. The progress of the AI agent's work is presented through a user-friendly web interface, allowing users to monitor the research process in real-time.
Initially designed to answer crypto research topics, BlockAGI has proven useful for a wide variety of other use cases. Its automated research capabilities, comprehensive search functionality, and live data access make it a valuable tool for researchers, analysts, and enthusiasts in various domains.
BlockAGI offers several key features that make it a powerful research assistant:
Automated Research: BlockAGI simplifies the research process by automating the gathering, refining, and evaluation of information. Users only need to provide the research topics, and BlockAGI takes care of the rest.
Comprehensive Search: BlockAGI can search for relevant information from various sources, ensuring a comprehensive coverage of the research topics. It utilizes LangChain and OpenAI to access a wide range of data and extract valuable insights.
Live Data Access: BlockAGI can access real-time data from the internet or your own database, allowing users to stay up-to-date with the latest information and trends in their research domain.
WebUI: BlockAGI is equipped with a user-friendly web interface that provides an interactive and intuitive experience. Users can monitor the agent's decision-making process, execution progress, and the latest research results through the web interface.
Hackable Code: The codebase of BlockAGI, based on LangChain, is concise and easy to modify. Users can customize and extend the functionality of BlockAGI to suit their specific research needs.
Privacy Focused: BlockAGI prioritizes user privacy and data security. The generated research reports stay with the user and the trusted LLM provider, ensuring confidentiality and control over the research findings.
Inspired by the Best: BlockAGI builds upon the work of BabyAGI and AutoGPT to create a self-improving research agent. It incorporates the best practices and techniques from these projects to enhance its performance and capabilities.
🛠️ Tech Stack
BlockAGI utilizes a powerful tech stack to deliver its functionality:
- Backend: Python and LangChain
- Frontend: Next.js and Tailwind
The backend is built with Python, leveraging the capabilities of LangChain for data processing and analysis. The frontend is developed using Next.js, a popular React framework, and styled with Tailwind CSS for a modern and responsive user interface.
To get started with BlockAGI, follow these steps:
Install Poetry, a dependency management tool for Python.
Clone the BlockAGI repository to your local machine.
Navigate to the project directory and run the following command to install the required dependencies:
Install the Playwright dependencies by running the following command:
poetry run playwright install
These steps will set up the necessary dependencies for BlockAGI and prepare it for usage.
🎮 Basic Usage
To start using BlockAGI, follow these steps:
.env.examplefile and rename it to
.envfile and add your OpenAI API key. You can also modify other configurations as needed, such as the research domain or additional settings.
Run the following command to start BlockAGI:
poetry run python main.py
This command will initiate BlockAGI and launch the web application, allowing you to monitor the research progress and interact with the agent.
Access the BlockAGI web interface to observe the progress and results of the research.
📥 Contribution and Feedback
Contributions, feedback, and suggestions are highly encouraged and appreciated for BlockAGI. You can contribute to the project in the following ways:
Fork the repository, make modifications in your own branch, and submit a pull request (PR) with your changes.
Submit issues on the GitHub repository to report bugs, suggest new features, or ask questions.
Join the Discord community of BlockAGI to share your experiences, ideas, and improvements with other users and developers.
Collaborative development and community engagement are essential for the growth and improvement of BlockAGI.
BlockAGI provides comprehensive documentation to guide users in installation, usage, and customization. The documentation covers the following topics:
- Installation and Basic Usage
- Parameters and Their Recommended Values
- BlockAGI's Architecture
- Design Choices
- Building Custom Tools
- Hacking Your Own Research Assistant (Advanced)
- Contributing to BlockAGI
The documentation serves as a valuable resource for users to explore and maximize the potential of BlockAGI.
BlockAGI is an open-source software licensed under the Apache License 2.0. This license allows users to use, modify, and distribute the software. For complete details, please refer to the LICENSE and NOTICE files in the BlockAGI repository.
BlockAGI acknowledges the inspiring work and contributions of the following projects and communities:
These projects have laid the foundation for BlockAGI and have influenced its development and capabilities.