// Documentation
Build the memory layer from laptop to cloud.
Quickstarts, agent integrations, cloud deployment guides, and the reference material needed to operate greatmemory with confidence.
Local quickstart
Install gmem, start the server, store and search your first memory - all on your own machine.
Read guide →Getting startedServer quickstart
Auth, CORS, SQLite vs Postgres, and Docker Compose for a server other machines can reach.
Read guide →Getting startedIngest, use, and remove data
Public examples for adding text and files, using memory in prompts, and deleting imported data by id.
Read guide →CapabilitiesFeature 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 →AgentsMCP server
Both transports, the five tools with parameters and examples, and space conventions.
Read guide →AgentsClaude Code
Persistent memory for Claude Code with one command.
Read guide →AgentsCodex CLI
Register gmem mcp in ~/.codex/config.toml.
Read guide →AgentsHermes
stdio MCP configuration for Hermes.
Read guide →AgentsOpenClaw
stdio MCP configuration for OpenClaw.
Read guide →AgentsCustom agents (REST)
curl, Python, and TypeScript clients for the memory loop, plus OpenAPI client generation.
Read guide →IntegrationsGoogle Vertex AI
Use Vertex AI as greatmemory's LLM and embedder via the OpenAI-compatible endpoint - models, OAuth token auth, and embedding dimensions.
Read guide →IntegrationsAmazon Bedrock
Use Amazon Bedrock for fact extraction and reflection via the OpenAI-compatible Chat Completions endpoint and a Bedrock API key.
Read guide →IntegrationsAzure OpenAI
Use Azure OpenAI (Azure AI Foundry) as greatmemory's LLM and embedder via the OpenAI-compatible v1 API and deployment names.
Read guide →IntegrationsCloud ETL & data management
Managed ETL patterns for Dataflow, Azure Data Factory, and AWS Glue: ingest, use, update, and delete greatmemory data.
Read guide →DeploymentAWS
EC2 + Docker Compose, or ECS Fargate with RDS Postgres + pgvector.
Read guide →DeploymentAzure
Container Apps with Azure Files or PostgreSQL Flexible Server; Container Instances as the simple path.
Read guide →DeploymentGoogle Cloud
Cloud Run with Cloud SQL + pgvector, or a GCE VM with a stateful disk.
Read guide →DeploymentEnterprise database (pgvector)
Run greatmemory against managed/enterprise Postgres where a DBA provisions pgvector and the app role can't CREATE EXTENSION.
Read guide →DeploymentUpgrades & migrations
Zero-downtime version upgrades: automatic migrations, the readiness probe, rolling deploys, and safe rollback.
Read guide →ReferenceCLI reference
Every gmem command and flag, client environment variables, exit codes.
Read guide →ReferenceConfiguration reference
Every environment variable, greatmemory.toml key, CLI flag, and feature toggle in one place.
Read guide →ReferenceArchitecture & integration
The single-workspace deployment model, control plane, core engine, request flow, and integration surfaces.
Read guide →ReferenceAPI keys & air-gapped use
Creating, rotating, and verifying API keys - and running with no internet access at all.
Read guide →ResearchResearch & roadmap
The memory-systems research that informs greatmemory - temporal knowledge graphs, agentic memory, reflection - and how each idea maps onto the engine.
Read guide →