# Eion | Connecting AI Agents Through Shared Memory And Collaborative Intelligence

**URL:** <https://onehack.st/t/eion-connecting-ai-agents-through-shared-memory-and-collaborative-intelligence/307376>\
**Category:** Tools & Scripts\
**Tags:** tools, programming, technology, ai\
**Created:** [June 26, 2025, 9:49pm UTC](https://onehack.st/t/eion-connecting-ai-agents-through-shared-memory-and-collaborative-intelligence/307376 "2025-06-26T21:49:04Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![NoBody](https://onehack.st/user_avatar/onehack.st/nobody/32/163880_2.png) [@NoBody](https://onehack.st/u/NoBody)\
**Post date:** [June 26, 2025, 9:49pm UTC](https://onehack.st/t/eion-connecting-ai-agents-through-shared-memory-and-collaborative-intelligence/307376/1 "2025-06-26T21:49:04Z")

</div>

[![Eion Logo](https://github.com/eiondb/eion/raw/main/assets/eion-cream.png#gh-dark-mode-only)](https://github.com/eiondb/eion/blob/main/assets/eion-cream.png#gh-dark-mode-only)

# Eion

_Connecting AI agents through shared memory and collaborative intelligence._

[![Version](https://camo.githubusercontent.com/6d89583255a0e1bc64162aff7c9d8ced2583decec30eee029fbfa6312974f876/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f56657273696f6e2d76302e312e332d677265656e)](https://camo.githubusercontent.com/6d89583255a0e1bc64162aff7c9d8ced2583decec30eee029fbfa6312974f876/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f56657273696f6e2d76302e312e332d677265656e) [![License: AGPL v3](https://camo.githubusercontent.com/8d00b0d97ebc54b5e908a5f5a73c9d613efee6138d46b620f3084d2fba9d455e/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f4c6963656e73652d4147504c5f76332d626c75652e737667)](https://www.gnu.org/licenses/agpl-3.0)

[![Eion Demo](https://github.com/eiondb/eion/raw/main/assets/eion-demo.gif)](https://github.com/eiondb/eion/blob/main/assets/eion-demo.gif)

**Eion** is a shared memory storage that provides unified knowledge graph capabilities for multi-agent systems, adapting to different AI deployment scenarios from single LLM applications to complex multi-agency systems.

### 1. LLM Application

```auto
User ↔ LLM Application → Eion (context storage)

```

### 2. AI Agent Application

```auto
Business Logic ↔ AI Agent → Eion (memory + knowledge graph)

```

### 3. Agency (Multi-Agent) Systems

#### 3a. Sequential Agency

```auto
Agent A → context → Agent B → context → Agent C
                ↓ ↓ ↓
              Eion ← shared memory & knowledge → Eion

```

#### 3b. Concurrent Live Agency (WIP)

```auto
Agent A ──┐
          ├── shared live context ← Eion (live sync + notifications)
Agent B ──┤
          │
Agent C ──┘

```

### 4. External Guest Agent Access

```auto
Internal Agency: Agent A ↔ Agent B → Eion ← External Agent C (guest)
                                            ↑
                                    (controlled access)

```

## Quick Start

### Prerequisites

- **Docker & Docker Compose** : For PostgreSQL and Neo4j
- **Go 1.21+** : For the Eion server
- **Python 3.13+** : For knowledge extraction services

### 1. Clone and Setup

```auto
git clone <repo>
cd eion

```

### 2. Start Database Services

```auto
# Start all required databases (PostgreSQL + Neo4j)
docker-compose up -d

# Verify databases are ready
docker-compose ps

```

### 3. Setup Database Extensions and Tables

```auto
# Enable the pgvector extension (required for embeddings)
docker exec eion_postgres psql -U eion -d eion -c "CREATE EXTENSION IF NOT EXISTS vector;"

# Run main orchestrator migrations (includes sessions table)
docker exec -i eion_postgres psql -U eion -d eion < database_setup.sql

```

### 4. Install Python Dependencies

```auto
# Create virtual environment
python3 -m venv .venv
source .venv/bin/activate # On Windows: .venv\Scripts\activate

# Install dependencies
pip install -r requirements.txt

```

### 5. Build and Run Eion Server

```auto
# Build the server
go build -o eion-server ./cmd/eion-server

# Run the server
./eion-server

```

### 6. Verify Setup

```auto
# Check server health
curl http://localhost:8080/health

# Expected response:
# {"status":"healthy","timestamp":"2024-12-19T10:30:00Z","services":{"database":"healthy","embedding":"healthy"}}

```

## Architecture

Eion provides a unified API that combines:

- **Memory Storage** : PostgreSQL with pgvector for conversation history and semantic search
- **Knowledge Graph** : Neo4j with in-house extraction for temporal knowledge storage
- **Real Embeddings** : `all-MiniLM-L6-v2` model (384 dimensions) using sentence-transformers - production-ready embeddings
- **Knowledge Extraction** : In-house extraction service for entity/relationship extraction

## Configuration

Create `eion.yaml` (optional - defaults work out of the box):

```auto
common:
  http:
    host: "0.0.0.0"
    port: 8080
  
  postgres:
    user: "eion"
    password: "eion_pass" 
    host: "localhost"
    port: 5432
    database: "eion"
  
  # Neo4j Configuration (Required)
  numa:
    neo4j:
      uri: "bolt://localhost:7687"
      username: "neo4j"
      password: "password"
      database: "neo4j"

```

## Additional Configuration

For production deployments, you may want to customize the database settings in `docker-compose.yml` or create your own configuration.

Or use the automated setup script:

```auto
# One-command setup (includes database startup, Python env, and server build)
./setup.sh

# Then start the server
./eion-server

```

* * *

## GitHub:

> **[GitHub - eiondb/eion: Shared Memory Storage for Multi-Agent Systems](https://github.com/eiondb/eion)**
>
> Shared Memory Storage for Multi-Agent Systems