OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Memory & RAG

Eion

Eion is shared-memory infrastructure for LLM applications and multi-agent systems. It stores conversation context and provides knowledge-graph capabilities, with a built-in MCP server that exposes tools for memory and knowledge operations.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Eion — OpenViST project profile in Agent Memory & RAG.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Consider Eion when an application needs a separately operated memory and knowledge layer shared by an LLM or multiple agents, particularly when MCP tools fit the integration approach.

Who it is for

  • Developers building AI-agent applications that need shared conversation context.
  • Teams coordinating sequential agents that need access to earlier context.
  • Builders seeking an MCP-based route for agents to use memory and knowledge tools.

Documented uses

  • Store and retrieve conversation messages for agent sessions.
  • Search stored conversations semantically.
  • Create, search, update and delete knowledge entries.
  • Share context and knowledge across agents in a workflow.
Before you choose

Requirements & limits

The project is public source code under the AGPL-3.0 license. The README documents a self-hosted setup; it does not establish hosted-service terms or pricing.

  • The documented stack includes PostgreSQL with pgvector, Neo4j, a Go server and Python dependencies.
  • The MCP server exposes four memory tools and four knowledge tools for agent integration.
  • Concurrent live context synchronization is marked work in progress in the README.
  • The project describes controlled guest-agent access, while specific deployment and access configuration details require further documentation.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up Eion’s documented local server stack

Prepare the database services, install dependencies, build the Eion server and check its documented health endpoint.

Before you start

  • Docker and Docker Compose for PostgreSQL and Neo4j
  • Go 1.21 or later
  • Python 3.13 or later
  • A clone of the Eion repository

Steps

  1. Clone the repository and change into its directory.

  2. Start the PostgreSQL and Neo4j services with Docker Compose.

  3. Enable the pgvector extension and apply database_setup.sql to PostgreSQL.

  4. Create a Python virtual environment and install requirements.txt.

  5. Build and run the server, then request the documented localhost health endpoint.

Expected outcome

The README describes a running server at localhost:8080 and a health response covering database and embedding services.

Guide limitations

  • This setup recipe does not cover connecting a particular agent or configuring a production deployment.
  • The README labels concurrent live context synchronization as work in progress.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
17 October 2026
Original website title
eiondb/eion · Official homepage title · retained in its source language
How we review sourcesSuggest a correction