endee-io/endee

Endee.io – A high-performance vector database, designed to handle up to 1B vectors on a single node, delivering significant performance gains through optimized indexing and execution. Also available in cloud https://endee.io/

What it solves

Endee provides a high-performance retrieval layer for AI applications that need to search through large amounts of data quickly. It solves the problem of efficiently managing and querying high-dimensional vectors, allowing developers to implement semantic search, RAG pipelines, and long-term memory for AI agents without sacrificing speed or control.

How it works

Implemented in C++ and optimized for modern CPUs (supporting AVX2, AVX512, NEON, and SVE2), Endee functions as a search and intelligence platform. It combines dense vector retrieval with sparse search capabilities and payload filtering, enabling hybrid search where both semantic meaning and specific keyword precision are required. It exposes an HTTP API for managing indexes and serving retrieval workloads, and can be deployed via local builds or Docker.

Who it’s for

It is designed for teams building RAG pipelines, AI agents (using frameworks like LangChain or LlamaIndex), recommendation systems, and any application requiring low-latency, metadata-aware vector retrieval.

Highlights

  • Hybrid Retrieval: Supports both dense and sparse vector search for improved relevance.
  • Payload Filtering: Allows for structured retrieval logic based on metadata.
  • CPU Optimized: Specifically tuned for various CPU architectures to maximize performance.
  • Operational Readiness: Includes built-in backup APIs and runtime observability/logging.

Related

  • Project
    infiniflow/infinity

    An AI-native database designed for LLM applications that provides high-speed hybrid search across dense and sparse embeddings, tensors, and full-text data.

  • Project
    pathwaycom/llm-app

    A collection of ready-to-deploy AI pipeline templates for high-accuracy, real-time RAG and enterprise search that syncs directly with live data sources.

  • Project
    java-up-up/nexus-agent

    An enterprise-grade AI agent platform that implements a complete closed-loop of document governance, hybrid RAG retrieval, and ReAct-based autonomous agents for production environments.

  • Project
    weiwill88/Local_Pdf_Chat_RAG

    A modular Python implementation of a RAG pipeline designed for learning and experimentation, featuring hybrid retrieval and support for multiple LLM backends.

  • Project
    SHITIANYU-hue/SheetasToken

    A two-stage retrieval pipeline using a fine-tuned BGE encoder and a relational GNN to identify relevant sheets in multi-sheet spreadsheets based on metadata.