Practical overview
When it fits
Use Attu when you need a visual interface for administering Milvus, exploring vector data, searching collections, or monitoring and backing up clusters.
Who it is for
- Milvus administrators managing one or more clusters
- Data teams exploring collections and running vector searches
- Operators monitoring cluster health or managing backups
Documented uses
- Browse databases, collections and records; edit data inline; import or export CSV, JSON and Parquet.
- Run vector similarity searches and supported query or search aggregations.
- Manage backups, restores, partitions, schemas and collection data.
- Review cluster health, Prometheus metrics and topology.
- Use a configured AI agent to carry out supported Milvus management tasks through chat.
Requirements & limits
Attu is documented as a self-hosted web application or desktop application. The v3.0 documentation lists Docker, Kubernetes and a standalone server package for web use, plus desktop releases for macOS, Linux and Windows.
- Attu v3.0 supports Zilliz Cloud and open-source Milvus 2.6.0+ and 3.x; it does not support Milvus 2.5.x or earlier.
- The web app can be deployed with Docker, Kubernetes or the documented standalone Linux x64 server package; desktop builds are also listed.
- AI chat requires a supported model provider or custom API endpoint.
- The public GitHub repository does not have a license identified in the supplied project documentation.
Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.
Start Attu with Docker and connect to Milvus
Run the documented Attu v3.0.0 Docker image with a persistent data volume and a preconfigured Milvus endpoint.
Before you start
- Docker
- A reachable Zilliz Cloud or open-source Milvus 2.6.0+ or 3.x endpoint
Steps
Start the Attu container with port 3000 published, a named volume mounted at /data, and MILVUS_ADDRESS set to the Milvus gRPC endpoint.
Open http://localhost:3000.
Use the preconfigured connection to access the Milvus cluster.
Expected outcome
Attu is available in a browser on port 3000, with its saved application data stored in the named volume and a default Milvus connection configured.
Guide limitations
- Milvus 2.5.x and earlier are not supported by Attu v3.0.
- The documented host.docker.internal:19530 address is an example; the endpoint must be reachable from the container.
Compare options for Vector search
These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.
| Project | Documented purpose | Platform | Access and requirements |
|---|---|---|---|
| Attu | Browse databases, collections and records; edit data inline; import or export CSV, JSON and Parquet. | Docker, Self-hosted | Attu is documented as a self-hosted web application or desktop application. The v3.0 documentation lists Docker, Kubernetes and a standalone server package for web use, plus desktop releases for macOS, Linux and Windows. |
| Text-to-SQL Copilot | Ask questions about database contents in natural language. | CLI | The repository is public and MIT-licensed. The README describes Hugging Face Inference API access as free, and requires a Hugging Face API token for the documented model connection. |
Sources & review
Source record details
- Source availability
- Active
- Sources checked
- 18 October 2026
- Original website title
- zilliztech/attu · Official homepage title · retained in its source language