EKOS: Enterprise Knowledge Compiler for AI Agents

Repositoryalexeyban/EKOSTool

EKOS (Enterprise Knowledge Operating System) is an open-source Rust-based platform designed to observe, compile, and serve enterprise knowledge from disparate sources via the Model Context Protocol (MCP) for AI agents.

Key points

  1. Extracts and deterministically compiles knowledge from source code, Git history, SQL schemas, GitHub issues, Confluence, and files into a Canonical Knowledge Model.
  2. Stores derived facts in an append-only ledger where every conclusion references its originating evidence.
  3. Provides AI agents (such as Claude Code) read access via a dedicated Model Context Protocol (MCP) server (RFC 0013), isolating raw enterprise systems.
  4. Benchmark testing on the plausible/analytics repo (2,022 files) reported a 67–93% reduction in token usage for queries compared to raw grep-based searches.
  5. Built in Rust (2024 edition) under an MIT license, using an RFC-driven development workflow.

Why it matters

Enterprise knowledge is frequently fragmented across codebases, databases, and wikis, leading to information loss and inefficient context ingestion for LLMs. EKOS aims to compile these inputs into a structured ledger, lowering token costs and reducing AI hallucinations by retaining strict evidence traces.

Analysis

Rather than acting as a simple vector database or document store, EKOS treats enterprise data as input to a compiler pipeline. The use of MCP aligns with modern AI agent integration patterns. However, the repository is at a very early development stage with minimal community traction (10 stars) and introduces a community token model, which may raise questions regarding enterprise adoption.

Mentioned links

Found in

Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.

Related entries

Similar in content, found by the AI search.

  • Repository:DeusData/codebase-memory-mcp

    codebase-memory-mcp: High-Performance Knowledge-Graph Code Intelligence via MCP

    codebase-memory-mcp is a pure C Model Context Protocol (MCP) server that indexes codebases into persistent knowledge graphs, providing AI coding agents with sub-millisecond structural search while dramatically reducing token consumption.

    42.3kstarsC

    AI & LLMs· Tool

  • Repository:GoogleCloudPlatform/knowledge-catalog

    Google Cloud Knowledge Catalog: Tools and Samples for Semantic AI Agents

    The GoogleCloudPlatform/knowledge-catalog repository gathers tools, agents, and sample code for Google Cloud's Knowledge Catalog (formerly Dataplex). The platform functions as an AI-powered data catalog and metadata management system, organising structured and unstructured data into a dynamic knowledge graph to deliver business context to AI agents.

    9.1kstarsTypeScript

    AI & LLMs· Tool

  • Repository:EveryInc/compound-engineering-plugin

    Compound Engineering: 33-Skill Plugin for AI Coding Agents

    Compound Engineering is an open-source plugin for AI coding agents designed to structure development workflows and systematically preserve learned context. It runs on 14 platforms, including Claude Code, Cursor, and Codex.

    24.9kstarsTypeScript

    AI & LLMs· Tool

  • Link:agentwikis.com

    Agent Wikis: Maintained Knowledge Bases for Humans and AI Agents

    Agent Wikis transforms fast-moving information sources such as repositories, changelogs, transcripts, and community Q&A into structured Markdown knowledge bases. Designed for both humans and AI agents, the content is accessible via an llms.txt entry point.

    AI & LLMs· Resource

Back to the knowledge base

Let's talk about your project

Get in touch

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.