---
title: "Concepts"
url: "https://docs.mekodata.ai/concepts/"
---

# Concepts

What Meko is, and the kinds of context an agent keeps in a datapack

Multi-agent applications don't fail because agents can't reason; they fail because they can't share what they know. An agent needs to remember preferences, use knowledge, and keep its conversation history, efficiently and alongside other agents doing the same.

The usual answer bolts together PostgreSQL, pgvector, a separate memory store, and an object store for conversations. That splits the data into silos, adds cross-system latency, and leaves you writing the tiering and observability yourself. Meko replaces it with one data layer behind one MCP endpoint.

Read these pages in order. Each assumes only the ones before it.

![Meko Concepts Diagram](/images/meko-concepts.svg)

[**What is Meko**  
\
Where Meko sits in your architecture, what it replaces, and how it deploys.](/concepts/what-is-meko/)

[**Datapacks**  
\
The isolation unit for agents working together. Each datapack bundles a database, the knowledge base, memories, and credentials.](/concepts/datapacks/)

[**Memory**  
\
Durable facts, preferences, and decisions Meko extracts from conversations.](/concepts/memory/)

[**Knowledge bases**  
\
Documents chunked, embedded, and indexed for retrieval.](/concepts/knowledgebase/)

[**Artifacts**  
\
Agent-generated files stored and retrieved whole, across sessions and agents.](/concepts/artifacts/)

[**Conversations and traces**  
\
Every conversation from prompt through chain-of-thought, including the memory and knowledge calls and the queries they ran.](/concepts/traces/)

[**Where to store it**  
\
How to choose between memories, knowledge base files, and artifacts.](/concepts/where-to-store/)

[**How Meko learns**  
\
How Meko ranks what it retrieves, how private memory becomes knowledge the team shares, and what \[searches found\](/concepts/how-meko-learns/self-learning/).](/concepts/how-meko-learns/)