infinity

The AI-native database built for LLM applications, providing incredibly fast hybrid search of dense vector, sparse vector, tensor (multi-vector), and full-text.

4.4k
Stars
+205
Gained
4.9%
Growth
C++
Language

💡 Why It Matters

Infinity addresses the challenge of efficiently managing and searching through vast datasets, particularly in AI and ML applications. It offers a production-ready solution for teams needing fast hybrid search capabilities across dense and sparse vectors, making it ideal for ML/AI teams focused on large language models (LLMs). With a solid maturity level and active community support, it is a reliable choice for production environments. However, it may not be suitable for teams with simpler search requirements or those not leveraging advanced AI techniques.

🎯 When to Use

Infinity is a strong choice when teams require rapid and efficient search capabilities for complex datasets in AI applications. Consider alternatives if your project does not involve large-scale data or if simpler search functionalities suffice.

👥 Team Fit & Use Cases

This open source tool for engineering teams is primarily used by ML engineers, data scientists, and AI researchers. It typically integrates into products and systems that require advanced search functionalities, such as recommendation engines, search platforms, and data analysis tools.

🎭 Best For

🏷️ Topics & Ecosystem

ai-native approximate-nearest-neighbor-search bm25 cpp20 cpp20-modules embedding full-text-search hnsw hybrid-search information-retrival multi-vector nearest-neighbor-search rag search-engine tensor-database vector vector-database vector-search vectordatabase

📊 Activity

Latest commit: 2026-02-13. Over the past 96 days, this repository gained 205 stars (+4.9% growth). Activity data is based on daily RepoPi snapshots of the GitHub repository.