Documentation

Build the memory layer from laptop to cloud.

Quickstarts, agent integrations, cloud deployment guides, and the reference material needed to operate Meivo with confidence.

Getting started

Local quickstart

Install gm-server, start the core engine, and store and recall your first memory locally.

Read guide →
Getting started

Server quickstart

Auth, CORS, SQLite vs Postgres, and Docker Compose for a server other machines can reach.

Read guide →
Getting started

Ingest, use, and remove data

Public examples for adding text and files, using memory in prompts, and deleting imported data by id.

Read guide →
Capabilities

Feature guide

Every capability explained for both decision-makers and engineers - what it does, how to enable it, an example, the benefits, and the trade-offs.

Read guide →
Agents

MCP server

Both transports, thirteen memory tools, parameters, examples, and namespace/security boundaries.

Read guide →
Agents

Claude Code

Persistent memory for Claude Code with one command.

Read guide →
Agents

Codex CLI

Register gm-server mcp in ~/.codex/config.toml.

Read guide →
Agents

Hermes

stdio MCP configuration for Hermes.

Read guide →
Agents

OpenClaw

stdio MCP configuration for OpenClaw.

Read guide →
Agents

Custom agents (REST)

curl, Python, and TypeScript clients for the memory loop, plus OpenAPI client generation.

Read guide →
Integrations

Google Vertex AI

Use Vertex AI as Meivo's LLM and embedder via the OpenAI-compatible endpoint - models, OAuth token auth, and embedding dimensions.

Read guide →
Integrations

Amazon Bedrock

Use Amazon Bedrock for fact extraction and reflection via the OpenAI-compatible Chat Completions endpoint and a Bedrock API key.

Read guide →
Integrations

Azure OpenAI

Use Azure OpenAI (Azure AI Foundry) as Meivo's LLM and embedder via the OpenAI-compatible v1 API and deployment names.

Read guide →
Integrations

Cloud ETL & data management

Managed ETL patterns for Dataflow, Azure Data Factory, and AWS Glue: ingest, use, update, and delete Meivo data.

Read guide →
Deployment

AWS

EC2 + Docker Compose, or ECS Fargate with RDS Postgres + pgvector.

Read guide →
Deployment

Azure

Container Apps with Azure Files or PostgreSQL Flexible Server; Container Instances as the simple path.

Read guide →
Deployment

Google Cloud

Cloud Run with Cloud SQL + pgvector, or a GCE VM with a stateful disk.

Read guide →
Deployment

Enterprise database (pgvector)

Run Meivo against managed/enterprise Postgres where a DBA provisions pgvector and the app role can't CREATE EXTENSION.

Read guide →
Deployment

Upgrades & migrations

Zero-downtime version upgrades: automatic migrations, the readiness probe, rolling deploys, and safe rollback.

Read guide →
Reference

Server command reference

The actual gm-server operational commands, plus pointers to REST/OpenAPI and MCP for memory operations.

Read guide →
Reference

Configuration reference

Core-engine environment variables, greatmemory.toml keys, operational flags, and feature toggles.

Read guide →
Reference

Architecture & integration

The enterprise memory framework, supporting gateway/UI, trust boundaries, deployment modes, and integration surfaces.

Read guide →
Reference

Core API keys & offline use

Direct core-engine API keys, offline operation, and the controls required for a sealed deployment.

Read guide →
Research

Research & roadmap

The memory-systems research that informs Meivo - temporal knowledge graphs, agentic memory, reflection - and how each idea maps onto the engine.

Read guide →