# opencurve/curve

Curve is a sandbox project hosted by the CNCF Foundation. It's cloud-native, high-performance, and easy to operate. Curve is an open-source distributed storage system for block and shared file storage.

Repository: https://github.com/opencurve/curve
Canonical: https://ross.abutalabs.com/products/curve
Homepage: https://opencurve.io
Language: C++
License: Apache-2.0
License Family: permissive
Topics: storage, distributed-systems, raft, sds, cloud-native-storage, high-performance, block-storage, filestorage, storage-engine, posix-compatible, fuse-filesystem, opensource, kubernetes
Last push: 2024-08-13T01:46:12+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2254, "days_push": 751, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2387, forks 522 (observed 2026-08-28T04:06:42.714816+00:00)

## What it is
Curve is a cloud-native distributed storage system developed by NetEase and hosted as a CNCF sandbox project, supporting both block storage (CurveBS) and POSIX-compatible shared file storage (CurveFS). It emphasizes high performance with RDMA+SPDK, easy operation, and hybrid cloud tiering of hot and cold data.

## Use cases
- deploy distributed block storage for virtual machine and container persistent volumes
- provide POSIX-compatible shared file storage for AI training workloads
- tier hot data on-premises and cold data to public cloud object storage
- build storage-compute separation architecture for databases like MySQL and Kafka
- replace proprietary cloud disks with self-hosted high-performance storage
- run cost-effective shared file storage on public cloud

## When to choose
- you need self-hosted distributed block or file storage with cloud-native deployment
- you want high-performance, low-latency storage using RDMA and SPDK
- you need hybrid tiering between local IDC and public cloud
- you want a CNCF-hosted, Kubernetes-friendly storage system

## When to avoid
- you only need simple single-node local storage
- you require a fully mature CNCF graduated project with large ecosystem
- your workload is Windows or macOS based
- you need object storage as the primary interface

## Facets
- artifact type: service
- maturity: active
- function: file-system, self-hosted, cloud
- domain: microservices, cloud-computing, infrastructure-as-code, big-data
- platform: self-hosted, cpp
- tags: distributed-storage, block-storage, shared-file-storage, fuse-filesystem, raft, rdma, spdk, posix-compatible, cncf-sandbox, storage-compute-separation, storage, containers, linux, docker, kubernetes

## Member repositories
- opencurve/curve (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:42.714816+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:34:35.222137+00:00, confidence not recorded.
  - readme: https://github.com/opencurve/curve (fetched 2026-08-28T04:06:42.714816+00:00, sha ee6c4b7444e7)
- Data as of 2026-08-30T08:39:29.467469+00:00.