cacheport

CP-04 · Service

CI cache storage that sits next to your runners

CI Cache stores the caches your pipelines save and restore: dependency folders, toolchains, build directories. It keeps them in the same region as your runners, with limits sized for real projects.

CP-04Manifest
GitHub Actions
cacheport/cache, same inputs as actions/cache
GitLab CI
S3-compatible runner cache
Other CI
cacheport cache save / restore
Entry size
Up to 20 GB per entry
Retention
Least recently used within your quota
Scope
Per repository and branch, with fallbacks

Everything in CI Cache

Drop-in for actions/cache

Change the uses: line. Keys, restore-keys and paths keep working.

S3 storage for GitLab runners

Point the distributed runner cache at Cacheport and every runner shares the same cache.

Self-hosted runners

Ephemeral runners start with a warm cache from the same region instead of an empty disk.

Larger limits

Quotas sized per workspace, not per repository, with entries up to 20 GB.

Branch fallbacks

Restore from the default branch when a feature branch has no cache of its own yet.

Visibility

See which keys hit, which miss and how much time restores take.

Up and running in three steps

  1. Step 1

    GitHub Actions

    Swap actions/cache for the Cacheport action.

    terminal
    - uses: cacheport/cache@v1
      with:
        path: ~/.cache/pip
        key: pip-${{ hashFiles('requirements.txt') }}
        restore-keys: pip-
        token: ${{ secrets.CACHEPORT_TOKEN }}
  2. Step 2

    GitLab Runner

    Configure the distributed cache in the runner's config.toml.

    config
    [runners.cache]
      Type = "s3"
      Shared = true
      [runners.cache.s3]
        ServerAddress = "acme.cacheport.cc"
        BucketName = "gitlab-cache"
        AccessKey = "ci"
        SecretKey = "<CACHEPORT_TOKEN>"
  3. Step 3

    Any other CI

    Use the CLI to save and restore any directory.

    ci log
    $ cacheport cache restore deps-$HASH node_modules
    $ npm ci
    $ cacheport cache save deps-$HASH node_modules

The numbers

Limits per plan are on the pricing page.

IntegrationsGitHub Actions (cacheport/cache), GitLab Runner (S3 cache), CLI for Buildkite, Jenkins, CircleCI and others
RegionsFrankfurt (fra1), Ashburn (iad1), San Jose (sjc1), Singapore (sin1), Sydney (syd1)
Largest entry20 GB
Compressionzstd, multi-threaded
RetentionLeast recently used within the workspace quota; entries unused for 30 days are removed

Setup guides by package manager

All 18 →

Where it pays off first

Self-hosted runner fleets

Caches live next to your runners instead of in a distant cloud region.

Big toolchains

Android SDKs, CUDA libraries and compiler toolchains restore in seconds instead of downloading again.

GitLab autoscaling

Autoscaled runners share one cache instead of each starting empty.

Questions

How is this different from Package Proxy?

Package Proxy caches individual packages from registries. CI Cache stores whole directories your pipeline saves. Many teams use both: CI Cache for the warm start, Package Proxy for whatever is missing.

Do I have to change my cache keys?

No. The GitHub action takes the same inputs as actions/cache.

Are caches shared between repositories?

No, entries are scoped per repository by default. You can opt in to shared keys for things like toolchains.

What happens when the quota is full?

The least recently used entries are removed first, so active branches keep their caches.

Same workspace, same tokens

Start on the free plan

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