Quick start

Get from zero to a working Meko integration in 60 seconds.

Sign up

1. Create a Meko account at the Meko portal.

2. Sign in to your account.

   Your default datapack (meko_default_datapack), is displayed. A datapack is a container for memory and knowledge.

3. Click Connect.

4. Copy the following MCP Server details and store them in a safe place:

   • Your MCP server URL.
   • Your MCP server API key.

Connect your AI client

A single setup command registers the Meko MCP server with your agent and installs the Meko skills package, so your agent knows when and how to use Meko's MCP tools for memory, knowledge, and conversation management.

Prerequisites

• Node.js 18+
• npm and npx (usually included with a standard Node.js install)
• Meko MCP Server URL and API key

Install

Run the following command to register the Meko MCP server and install the Meko skills package.

Replace the placeholders as follows:

• <mcp-client> — cursor, claude-code, or claude-desktop
• <mcp-server-url> — the MCP server URL you saved from the portal
• <mcp-server-api-key> — the MCP server API key you saved from the portal

npx @yugabytedb/meko-mcp --client <mcp-client> --url <mcp-server-url> --api-key <mcp-server-api-key>

npx @yugabytedb/meko-mcp --client all --url <mcp-server-url> --api-key <mcp-server-api-key>

Explore knowledge

Meko provides a persistent datastore for the full spectrum of information that AI agents need, from raw to refined:

• Conversations are one example of episodic information: raw, verbatim records of events, unfiltered and comprehensive. Episodic information captures everything that happened, relevant or not.
• Memory is derived from episodic information: extracted, condensed, and stored for associative retrieval. Memory trades completeness for efficiency and recallability.
• Knowledge is confirmed information — curated documents and facts that agents can rely on with confidence. Knowledge may be loaded directly or promoted from memory and conversations.

We'll start by exploring knowledge, then move on to memory — and in a later guide, see how conversation history can drive updates to both.

Upload knowledge

To see how Meko stores knowledge, add documents to your datapack and query them using RAG.

In your coding agent, issue a prompt to add to the knowledge base a document and attach a file in CSV, JSON, markdown, or PDF format.

As an example, for Claude Code, the standard for providing project knowledge and coding practices is a CLAUDE.md file. Use the following markdown content in Claude Code to try this out by copying and modifying the contents to a local CLAUDE.md file.

# Project Guidelines: Building agents to triage issues being logged by customers

## Overview
Build agents to triage issues being logged by Zendesk and create a Root Cause Analysis for it

## Tech Stack
- **Framework**: Next.js 15 (App Router)
- **Language**: TypeScript (Strict Mode)
- **Styling**: Tailwind CSS
- **Database**: Meko

## Core Coding Standards
- **Strict Typing**: Never use `any`. Define interfaces for all API responses.
- **Functional Style**: Prefer pure functions and immutable data patterns over classes.
- **Components**: Place reusable UI in `src/components/ui` and feature-specific logic in `src/features/*`.
- **Naming**: Use camelCase for variables/functions and PascalCase for components/types.

## Critical Commands
Specific bash commands Claude should use to verify its work:
- **Build**: `npm run build`
- **Lint**: `npm run lint`
- **Test**: `npm test` or `npm run test:watch`
- **Format**: `npm run format`

## Quality Check Workflow
IMPORTANT: After every significant code change, you MUST follow this sequence:
1. Run `npm run format` to ensure style consistency.
2. Run `npm run lint` to check for type errors or warnings.
3. Run `npm test` and fix any regressions before reporting completion.

## Project Gotchas & Patterns
- **Auth**: Always use the `useAuth()` hook; do not access session tokens directly from local storage.
- **API**: All external service calls must include a 3-second timeout and explicit error handling.

Use the CLI

You can also upload knowledge using the Meko CLI. See Meko CLI for installation instructions.

Upload documents to your datapack's knowledge base as follows:

meko datapack add_knowledge_base --name meko_default_datapack --url s3://bucket/docs/

Query your knowledge

Once your documents are parsed, chunked, and indexed by Meko, query them through your coding agent:

Search the knowledge base for information about <your topic>

The MCP server performs semantic search across your indexed documents and returns relevant chunks. In short, Meko has automated the retrieval augmented generation (RAG) pre-processing pipeline by reading, parsing, chunking, vectorizing/indexing the documents, and by providing a semantic search capability.

Explore memory

Meko uses memory to enhance user experience through personalization.

Ask this question of your coding agent without Meko:

Propose a 5 day vacation for me. Do not use Meko or any prior recollection of my preferences in generating your response.

Your AI either recommends a randomly-selected vacation, or perhaps asks generic follow-up questions such as "What kind of vacation?", "What budget?", or "To where?"

With Meko, however, your AI can remember your vacation preferences, and use them to generate better responses.

Create a memory

In your coding agent, do the following:

1. Tell the agent to store your preferences:

   You have access to the Meko platform through MCP server.
   Have Meko remember all my personal preferences.
   

2. Type the following to persist your personal preferences as memory:

   Please remember that I like to take vacations at tropical beach locations, on a budget
   

   Using the Meko MCP server, the agent will create a conversation in your datapack and assign an agent ID, for example, cursor_assistant. The agent should let you know what the agent ID is; you can also ask it.

3. Start a new chat session, then type the following (use the agent ID the other agent provided):

   Access my preferences using agent ID cursor_assistant.
   Propose a 5 day vacation for me.
   

Your AI can now leverage the memory to provide a more relevant response.

For example, Cursor can respond with something similar to the following:

Here’s a 5-day plan tuned to what you’ve saved: tropical beach + budget.

## Pick a base: Isla Holbox or Puerto Morelos area, Mexico (Yucatán)

Why it fits: Warm water, palm-lined beaches, easy buses from Cancún airport,
hostels / small hotels and street food keep costs down. (Swap-ins: Koh Lanta,
Thailand or Nusa Penida + Sanur, Bali if you’re already closer to Asia.)

<...>

---

## Budget levers

- Stay: hostel dorm or simple guesthouse slightly back from the sand (often 
  half the price of beachfront).
- Eat: markets, loncherías, set “menu del día” lunches; limit restaurant dinners.
- Move: buses + shared shuttles; avoid private taxis except airport if needed.
- Play: prioritize free swimming, walking, and one paid half-day trip instead
  of stacked tours.

---

## If you tell me your month, home airport region, and solo vs. group, I can
## narrow this to one place, rough daily spend, and a rain-day backup.

The agent retrieves your stored preferences and immediately proposes a vacation aligned to these preferences (a tropical beach vacation within budget). No follow-up questions are needed.

Check your memories

You can verify what Meko stored by checking your datapack's memories in the Meko portal. You'll see:

• The stored memories with their extracted entities
• Key metrics: number of memories, knowledge base sources, and MCP requests

Type:

What does Meko remember about me?

Observe your datapack

Check what's happening inside your datapack:

• Memories: View stored memories and their extracted entities.
• Knowledge bases: See indexed document sources and their status.
• Traces: Review LLM reasoning traces and execution logs.

Next steps

With your first datapack live, you can transition from a basic demo to a robust, context-aware development environment. Explore the following advanced capabilities to fully leverage Meko's persistent memory and knowledge graph.