cacheport

CP-01 · Service

One cache in front of every package registry

Package Proxy sits between your builds and the public registries. The first request for a package goes upstream; every request after that is served from a cache in the same region as your runners, with integrity checks intact.

CP-01Manifest
Registries
18, from npm and PyPI to apt and apk
Endpoint
https://acme.cacheport.cc/<registry>/
Regions
fra1, iad1, sjc1, sin1, syd1
Metadata
Refreshed every 5 min, stale copy on upstream failure
Artifacts
Immutable, stored per version
Auth
Scoped read tokens, CI-friendly

Everything in Package Proxy

Read-through caching

Nothing to pre-sync. Packages are fetched on first use and kept, so the cache matches what your builds actually need.

Upstream outage protection

If a registry slows down or goes offline, cached versions keep serving and metadata falls back to the last good copy.

Rate limit relief

Hundreds of runners look like one well-behaved client to the upstream, so shared NAT addresses stop tripping per-IP limits.

Release cooldown

Hold back versions younger than a set age. Fresh installs pick the newest version that has been public long enough to be vetted.

Allow and deny rules

Block a package, a version range or a whole scope across every repository at once, with the reason shown to whoever hits it.

Private upstreams

Add GitHub Packages, GitLab, Artifactory or your own registry behind the same URL. Private names never leak to public registries.

Audit log

Every pull is recorded with token, repository, package, version and outcome. Export to S3 or stream to your SIEM.

Cache-Status headers

Each response says whether it came from the cache, from upstream or from a stale copy, using the standard Cache-Status header.

Up and running in three steps

  1. Step 1

    Create a workspace

    Sign up, pick the region closest to your runners and create a read token for CI.

    terminal
    $ cacheport login
    $ cacheport workspace create acme --region fra1
    $ cacheport token create ci --scope read
  2. Step 2

    Point your clients at it

    Each package manager needs one setting. Store the token as a CI secret.

    config
    registry=https://acme.cacheport.cc/npm/
    index-url = https://acme.cacheport.cc/pypi/simple/
    GOPROXY=https://acme.cacheport.cc/go,direct
  3. Step 3

    Run your pipeline

    The first run warms the cache. From the second run on, the pull log shows hits.

    ci log
    $ npm ci
    added 1214 packages in 9s
    # Cache-Status: cacheport; hit

The numbers

Limits per plan are on the pricing page.

Supported registriesnpm, Yarn, pnpm, PyPI (pip, Poetry, uv), Conda, Maven, Gradle, Go modules, Cargo, RubyGems, Composer, NuGet, Docker Hub, Helm, apt, Alpine apk
RegionsFrankfurt (fra1), Ashburn (iad1), San Jose (sjc1), Singapore (sin1), Sydney (syd1)
ProtocolHTTPS only, TLS 1.2 and 1.3, HTTP/2
Metadata freshness5 minutes by default, configurable from 1 minute to 24 hours per registry
Largest single artifact10 GB
AuthenticationBearer tokens, Basic auth for clients that need it, OIDC from GitHub Actions and GitLab CI
Availability99.9% on Team, 99.95% on Business, custom on Enterprise

Setup guides by package manager

All 18 →

Where it pays off first

Monorepos with thousands of dependencies

Cold installs that took minutes come down to the time it takes to copy files from a nearby cache.

Self-hosted runner fleets

Runners behind one NAT address stop competing for the same per-IP limits on public registries.

Regulated builds

Every dependency a release used is recorded, kept and reproducible, even if it is later removed upstream.

Questions

Is a package cached for everyone in my workspace?

Yes. A workspace has one shared cache. The first repository to pull a version warms it for every other repository and runner.

What happens if a package is unpublished upstream?

Versions already in your cache stay available, so existing lockfiles keep installing. You can block a version yourself with a deny rule if you want it gone.

Does Cacheport modify packages?

Never. Artifacts are stored and served byte for byte, so checksums in lockfiles and go.sum files keep matching.

Can I use it from developer laptops too?

Yes. Create a personal token and use the same settings locally. Many teams do this to get the same dependency set in CI and on laptops.

Same workspace, same tokens

Start on the free plan

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