cacheport

CP-02 · Service

Pull-through cache for every container registry

Container Mirror caches images from public and private registries in the region of your runners and clusters. Pulls get faster, rate limits stop applying to images you already use, and digests stay identical.

CP-02Manifest
Registries
Docker Hub, GHCR, Quay, registry.k8s.io, MCR, ECR Public
Endpoint
acme.cacheport.cc/<registry>/<image>
Clients
Docker, Podman, containerd, CRI-O, BuildKit
Tags
Re-checked every 5 minutes
Layers
Cached by digest, deduplicated
Artifacts
Images, Helm charts and other OCI artifacts

Everything in Container Mirror

One host, many registries

Each upstream gets a short prefix: /hub, /ghcr, /quay, /k8s, /mcr. Add private registries with their own credentials.

Identical digests

Manifests and layers are served byte for byte, so image@sha256 references and signatures keep verifying.

Rate limit relief

Cacheport pulls upstream with one authenticated account. Your runners and nodes never hit the upstream directly.

Layer deduplication

Layers shared between images are stored once, so caching many tags of the same base image costs little.

Outage protection

If an upstream is down, cached tags keep resolving to their last known manifest.

Kubernetes ready

containerd and CRI-O can route docker.io and other registries through the mirror without changing image references.

Pull audit

Every pull is logged with token, image, digest and outcome.

Multi-arch

Each platform in a manifest list is cached as it is pulled.

Up and running in three steps

  1. Step 1

    Log in

    Create a read token and log in from your CI or node.

    terminal
    $ echo "$CACHEPORT_TOKEN" | docker login acme.cacheport.cc -u ci --password-stdin
    Login Succeeded
  2. Step 2

    Prefix your images

    Add the registry prefix to image references.

    config
    node:22-alpine
      -> acme.cacheport.cc/hub/library/node:22-alpine
    ghcr.io/org/app:1.4
      -> acme.cacheport.cc/ghcr/org/app:1.4
  3. Step 3

    Or mirror transparently

    On containerd, route docker.io through Cacheport without touching manifests.

    ci log
    # /etc/containerd/certs.d/docker.io/hosts.toml
    server = "https://registry-1.docker.io"
    
    [host."https://acme.cacheport.cc/v2/hub"]
      capabilities = ["pull", "resolve"]
      override_path = true

The numbers

Limits per plan are on the pricing page.

Supported upstreamsDocker Hub, GitHub Container Registry, Quay.io, registry.k8s.io, Microsoft Container Registry, Amazon ECR Public, any OCI-compliant private registry
RegionsFrankfurt (fra1), Ashburn (iad1), San Jose (sjc1), Singapore (sin1), Sydney (syd1)
ProtocolOCI Distribution Specification, Docker Registry HTTP API V2
Tag freshness5 minutes by default, configurable per upstream
Largest layer20 GB
AuthenticationToken via docker login, OIDC from GitHub Actions and GitLab CI, IP allowlists for nodes

Setup guides by package manager

All 18 →

Where it pays off first

Shared CI runners

Base images come from the cache instead of counting against Docker Hub limits for a shared address.

Kubernetes clusters

Node scale-ups pull images from the same region in seconds.

Air-gapped promotion

Pin the images you approve and serve them to environments that cannot reach the internet.

Questions

Do I have to change every image reference?

Not on containerd or CRI-O, where a hosts configuration routes docker.io through Cacheport. With Docker, prefix the references or use a build argument for the registry.

Can I push images?

No. Container Mirror is pull-only. Push to your own registry and add it as an upstream if you want it cached.

Are signatures preserved?

Yes. Cosign signatures and attestations are OCI artifacts and are mirrored like images.

How long are layers kept?

As long as a cached manifest references them, within your plan's storage. Unused layers are evicted least-recently-used.

Same workspace, same tokens

Start on the free plan

20 GB of cache, every registry, unlimited users. Upgrade when your pipelines outgrow it.