One command to run it all.
This repository holds the scripts served by install.memgraph.com: the quick start installers (init.sh, init.ps1) with their Docker Compose file, and the runnable code examples. Together they start the Memgraph ecosystem:
- MemgraphDB, including the MAGE graph algorithms
- mgconsole
- Memgraph Lab
- Memgraph Zero
The Docker images they use:
- Memgraph Docker image
- Memgraph Zero Docker image
- Memgraph MAGE Docker image
- Memgraph Lab Docker image
With Docker running on your system and ports 7687, 7444 and 3000 available, run one of the following commands to download the Memgraph Docker Compose file and start the Memgraph and Memgraph Lab services:
Linux/macOS
curl -sSL https://install.memgraph.com | bash
Windows
iwr https://install.memgraph.com/windows -useb | iex
By running docker ps, you'll notice memgraph-mage and memgraph-lab containers running. If you head over to localhost:3000, Quick Connect in Memgraph Lab will detect Memgraph running on your system. Check out the basic Docker Compose file and update it to fit your needs.
To start mgconsole, run the following command:
# with `docker ps` get the Memgraph container id
docker exec -ti <container-id> mgconsole
Each example is a runnable version of one of the Memgraph use cases: GraphRAG, AI Memory and Agentic AI. Each is a self-contained, end-to-end demo: it starts Memgraph in Docker, loads data, and runs real queries. Docker is the only requirement (AI Memory also needs Python 3.10-3.13). The walkthroughs live in code-examples/.
| Example | Linux/macOS | Windows |
|---|---|---|
| Agentic GraphRAG | curl -sSL https://install.memgraph.com/agentic-graphrag | bash |
iwr https://install.memgraph.com/agentic-graphrag/windows -useb | iex |
| AI Memory | curl -sSL https://install.memgraph.com/ai-memory | bash |
iwr https://install.memgraph.com/ai-memory/windows -useb | iex |
| Agentic AI | curl -sSL https://install.memgraph.com/agentic-ai | bash |
iwr https://install.memgraph.com/agentic-ai/windows -useb | iex |
The one-liners run the script straight from the web. To tear an example down,
run the downloaded script with clean (e.g. ./agentic-ai.sh clean or
.\agentic-ai.ps1 clean), or run the docker commands the example prints at the
end.