EKOS documentation
Compile enterprise knowledge for AI agents.
EKOS transforms source code, databases, documentation, and enterprise systems into a structured, traceable knowledge layer that AI agents can query without repeatedly rediscovering the underlying system.
Sources↓Knowledge Compilation↓Structured Knowledge↓MCP↓AI Agent↓Answer / Action
Get Started → Why EKOS? → Architecture → GitHub →
Understand the idea in 60 seconds. Run EKOS in 5 minutes. Understand the architecture in 20.
Start with the problem
AI Knowledge Layer for Enterprise SystemsAn open-source knowledge layer for AI agents: EKOS compiles code, SQL, docs and Git histor…MCP Server for Enterprise KnowledgeEKOS is an open-source MCP server that gives AI agents structured, evidence-backed knowled…AI Codebase Understanding for Large RepositoriesGive AI coding agents a persistent, evidence-backed understanding of a large codebase: cal…EKOS Benchmarks: Agent Tokens and Text-to-SQLHow many tokens an AI agent saves by querying compiled knowledge, and how much compiled kn…Enterprise Automation Use CasesEight enterprise automation use cases for EKOS with an orchestrator such as Dagster or Lan…PostgreSQL to Apache Iceberg PipelinesEKOS Lakehouse generates and governs PostgreSQL to Apache Iceberg medallion pipelines: bro…Pentaho to dbt ConverterAn open-source converter that translates Pentaho Data Integration (Kettle) .ktr and .kjb p…PostgreSQL to Apache Iceberg: CDC vs Scheduled LoadsHow to get PostgreSQL tables into Apache Iceberg: log-based CDC tools (Debezium, Flink CDC…Enterprise Knowledge Layer: Three Approaches ComparedAn enterprise knowledge layer can be a modelled knowledge graph, a governed metadata catal…codebase-memory-mcp vs EKOS: Code Knowledge Graph MCP Serverscodebase-memory-mcp and EKOS both give AI coding agents a persistent knowledge graph over …