Endee
A high-performance AI search and retrieval platform built for retrieval-augmented generation, semantic search, and hybrid search, designed to hold up to a billion vectors on a single node.
Endee is a search and retrieval platform for AI applications, combining dense vector retrieval with sparse search for hybrid search use cases, payload filtering for metadata-aware queries, backup workflows, and runtime observability. It targets teams building retrieval-augmented generation pipelines, semantic search, recommendation systems, and filtered vector retrieval APIs that need production-level performance.
It can also serve as the long-term memory and context retrieval layer for AI agents built with frameworks such as LangChain, CrewAI, AutoGen, and LlamaIndex, storing and retrieving past observations, tool outputs, and conversation history during a run. It deploys through local scripts, manual builds, or Docker images, and is optimized for CPU instruction sets including AVX2, AVX512, NEON, and SVE2.
It is written in C++ and released under the AGPL-3.0 license.