endee — What is it?

Endee is a high-performance vector database designed for AI search, RAG pipelines, semantic search, and hybrid retrieval, capable of handling up to 1B vectors on a single node.

⭐ 1,142 Stars 🍴 1,521 Forks C++ Apache-2.0 Author: endee-io
Source: Description per README View on GitHub →

Why it matters

Endee is gaining attention due to its specialized focus on vector databases for AI applications, offering hybrid retrieval support, payload filtering, and optimized CPU performance. Its unique technical choices include support for modern CPU targets and flexible deployment options.

Source: Synthesis of README and project traits

Core Features

Vector Search

Endee provides vector search capabilities optimized for AI retrieval and semantic similarity workloads, with support for dense vector retrieval and sparse search for hybrid use cases.

Source: README
Payload Filtering

Payload filtering allows metadata-aware retrieval and application-specific query logic, enhancing the precision of search results.

Source: README
Backup and Observability

Endee includes backup APIs and flows for data preservation and operational logging and instrumentation for runtime observability.

Source: README

Architecture

The architecture of Endee is inferred to be modular, with a clear separation of concerns. It likely employs design patterns such as the Model-View-Controller (MVC) for data management, search, and API interaction. The code tree indicates a focus on efficient data structures and indexing algorithms, with a significant portion of the codebase dedicated to the core search functionality.

Source: Code tree

Project Knowledge Graph

Knowledge graph: project (center) + core features (inner hexagons) + key dependencies (outer chips) Not enough informationNot enough inf… Vector Search Payload Filtering Backup and ObservabilityBackup and Observab… endee Project Core feature Key dependency

Center: project; inner ring: core feature modules; outer ring: key dependencies. Auto-generated from core_features and tech_stack.key_deps.

Tech Stack

LanguageC++FrameworkNot specified
Not enough information
Docker-based deployment options
Source: Dependency files + code tree

Quick Start

chmod +x ./install.sh ./run.sh ./install.sh --release --avx2 ./run.sh
Source: README Installation/Quick Start

Use Cases

Endee is suitable for AI search systems, RAG pipelines, semantic search, hybrid search, recommendation systems, and filtered vector retrieval APIs. It is useful in scenarios requiring fast vector search with metadata-aware filtering, such as AI agents, semantic search experiences, and hybrid search workflows.

Source: README

Strengths & Limitations

Strengths

  • Strengths: High-performance vector database optimized for AI applications, flexible deployment options, and support for hybrid search and payload filtering.

Limitations

  • Limitations: Limited information on third-party dependencies, and the project is relatively new with a small community.
Source: Synthesis of README, code structure and dependencies

Latest Release

v1.3.4 (2026-04-17): Release notes not provided.

Source: GitHub Releases

Verdict

Endee is a promising project for teams requiring a high-performance vector database for AI and search applications. Its focus on performance and flexibility makes it suitable for a wide range of use cases, particularly in the AI and semantic search domains.

Transparency Notice
This page is auto-generated by AI (a large language model) from the following public materials: GitHub README, code tree, dependency files and release notes. Analyzed at: 2026-05-23 00:06. Quality score: 85/100.

Data sources: README, GitHub API, dependency files