ESEILANE
A high-performance knowledge graph engine built for LLMs, GraphRAG and AI-native applications, using sparse matrix algebra for sub-millisecond graph traversals and full OpenCypher query support.
ESEILANE is a knowledge graph engine aimed at large-language-model and GraphRAG workloads, using GraphBLAS sparse matrix algebra and linear-algebra-based query execution for low-latency graph traversal at scale. It stores nodes and relationships as a property graph with rich attributes, supports the OpenCypher query language, and is built for horizontal scale with a pay-as-you-grow distributed architecture and multi-tenancy.
Enterprise features include role-based access control, audit logging, and encryption at rest and in transit. Its own published benchmarks compare node lookup, multi-hop traversal, complex Cypher queries, bulk inserts and GraphRAG context building against Neo4j and ArangoDB on the same class of cloud instance, reporting lower latency across each operation. The project's roadmap lists a Rust engine, a native vector index, a GraphQL API and a managed cloud offering as still in progress.
It installs as a Docker image, or as a client library from PyPI or npm, with the core engine being rewritten in Rust; client libraries are available in Python and TypeScript.