A curated list of awesome resources for applying LLMs and deep learning to financial market analysis and algorithmic trading.
Awesome AI in Finance is a curated GitHub repository listing open-source projects, research papers, tools, and datasets for applying artificial intelligence—particularly Large Language Models and deep learning—to financial markets. It solves the problem of information overload by providing a structured, community-vetted directory for developers and quants building automated trading systems, market analysis tools, and financial AI agents.
Quantitative developers, algorithmic trading researchers, data scientists in finance, and students looking for practical AI/ML resources and code for financial market applications.
Developers choose this list because it saves significant research time by aggregating high-quality, implementation-focused resources in one place. Its active community curation ensures relevance with the latest AI trends in finance, unlike static or commercial alternatives.
🔬 A curated list of awesome LLMs & deep learning strategies & tools in financial market.
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
Curates hundreds of open-source projects, papers, and datasets across domains like agents and LLMs, saving developers significant research time in AI-driven finance.
Organizes resources into clear categories such as Data Sources and Trading Systems, enabling targeted searches for specific financial AI applications.
Includes a Discord community badge, indicating active discussions that help keep the list updated with emerging trends and tools.
Focuses on cutting-edge areas like LLMs and deep reinforcement learning, reflecting the latest advancements in quantitative finance research.
As a community-curated list, it lacks rigorous vetting, so some linked projects may be outdated, poorly maintained, or of inconsistent quality without warnings.
Provides only brief descriptions and links, offering no tutorials, code reviews, or comparisons to help users evaluate or implement resources effectively.
With hundreds of external links, maintaining up-to-date information is challenging, and resources may become obsolete without frequent community updates.