1.89×
Faster builds
13.3 minutes less per build than the CI provider's cache, on the same runner class and commits.
Faster builds. Shared build data.
Reuse dependencies, compiler results, and task outputs across CI and local builds. Keep your build outputs and private images in the same workspace.
1.10×
Faster with half the vCPUs
Image builds on a runner with 8 vCPUs took less time on average than a remote builder with 16, and were faster on 24 of 30 shared commits.
2.7 ms
Median cache read time
Median of tool-reported project averages across 2 benchmarks. Hits can be served locally after prefetch.
PostHog
Average restore, build and save · lower is better
GitHub runner
4 vCPU · 16 GB · Ubuntu 24.04 x86-64
Base · Image layers
Plus · Image layers, tool caches and cache mounts
- Saved per build
- 13 min 20 s
- Faster than GHA Cache
- 1.89×
- Builds compared
- 30
1.96× on the 10 build pairs with the same CPU model
Depot runner
4 vCPU · 16 GB · Ubuntu 24.04 x86-64
Base · Image layers
Plus · Image layers, tool caches and cache mounts
Depot runner
8 vCPU · 32 GB · Ubuntu 24.04 x86-64
Base · Image layers
Plus · Image layers, tool caches and cache mounts
Depot remote builder
16 vCPU · 32 GB* · x86-64
* Builder sizes published by providers.
- Saved per build
- 36.0 s
- Faster than Depot builder, 16 vCPU
- 1.10×
- Builds compared
- 30
BoringCache on Depot runner, 8 vCPU: 5 min 58 s against 6 min 34 s on the builds both ran
Namespace runner
4 vCPU · 16 GB · x86-64
Base · Image layers
Plus · Image layers, tool caches and cache mounts
Namespace remote builder
8 vCPU · 16 GiB* · x86-64
* Builder sizes published by providers.
- Saved per build
- 47.5 s
- Faster than Namespace builder, 8 vCPU
- 1.08×
- Builds compared
- 18
BoringCache on Namespace runner, 4 vCPU: 9 min 16 s against 10 min 3 s on the builds both ran
Zed
Average restore, build and save · lower is better
GitHub runner
4 vCPU · 16 GB · Ubuntu 24.04 x86-64
Base · sccache compiler cache
Plus · sccache, Cargo registry and target directory
- Saved per build
- 8 min 33 s
- Faster than GHA Cache + target
- 1.28×
- Builds compared
- 30
1.21× on the 6 build pairs with the same CPU model
Depot runner · Zed release bundle
8 vCPU · 32 GB · Ubuntu 24.04 x86-64
- Saved per build
- 6 min 38 s
- Faster than Depot runner cache
- 1.51×
- Builds compared
- 30
1.48× on the 29 build pairs with the same CPU model
gRPC
Average restore, build and save · lower is better
GitHub runner
4 vCPU · 16 GB · Ubuntu 24.04 x86-64
- Saved per build
- 83.2 s
- Faster than BuildBuddy
- 1.49×
- Builds compared
- 9
1.33× on the 1 build pair with the same CPU model
n8n
Average restore, build and save · lower is better
GitHub runner
4 vCPU · 16 GB · Ubuntu 24.04 x86-64
- Saved per build
- 2 min 40 s
- Faster than GHA Cache
- 2.43×
- Builds compared
- 30
1.99× on the 11 build pairs with the same CPU model
Hugo
Average restore, build and save · lower is better
GitHub runner
4 vCPU · 16 GB · Ubuntu 24.04 x86-64
- Saved per build
- 49.7 s
- Faster than Depot Cache
- 2.19×
- Builds compared
- 18
2.26× on the 7 build pairs with the same CPU model
Lichess
Average restore, build and save · lower is better
GitHub runner
4 vCPU · 16 GB · Ubuntu 24.04 x86-64
- Saved per build
- 87.2 s
- Faster than GHA Cache
- 1.49×
- Builds compared
- 30
1.46× on the 8 build pairs with the same CPU model
Spring AI
Average restore, build and save · lower is better
GitHub runner
4 vCPU · 16 GB · Ubuntu 24.04 x86-64
- Saved per build
- 79.9 s
- Faster than Depot Cache
- 1.27×
- Builds compared
- 11
1.06× on the 2 build pairs with the same CPU model
OBS Studio
Average restore, build and save · lower is better
GitHub runner
4 vCPU · 16 GB · Ubuntu 26.04 x86-64
- Saved per build
- 11.8 s
- Faster than GHA Cache
- 1.11×
- Builds compared
- 28
1.28× on the 11 build pairs with the same CPU model
Compare build time, cache hits and stored cache across projects and tools. See all benchmarks →
Cache, Artifacts and Registry
Start with the part of your build you want to improve. Use the others when you need them.
Cache
Reuse dependencies, compiler results, task outputs, and Docker layers across compatible builds.
Explore Cache →Artifacts
Keep exact build outputs for testing, deployment, and release downloads. Choose their retention.
Explore Artifacts →Registry
Store private container images and pull them with your existing deployment tools.
Explore Registry →Keep your tools. Keep your runners.
Use BoringCache from hosted CI, self-hosted runners, and local development. Your build tools keep deciding which results are reusable.
All supported tools →Storage and access, in the same place.
Choose where build data is stored and which jobs can use it.
Where build data is stored
Managed storage
Every planCache · Artifacts · Registry
Included for Cache, Artifacts, and Registry on every plan. Start without setting up a storage account.
View plans →Your own storage
Custom planCache · Artifacts · Registry
S3
Azure Blob
Azure Blob
Connect S3-compatible storage for Cache, Artifacts and Registry on Custom. Cache and Artifacts also support Azure Blob Storage. Your provider bills storage and transfers.
Set up your storage →Separate readers and publishers
- Trusted CI jobs Publish shared cache for the next build Read + publish
- Pull requests Reuse cache without replacing it Read only
- Sandboxes and agents Reuse cache and keep new outputs local Read only
Connect supported CI through OIDC instead of keeping a reusable BoringCache secret in your workflow.
Compare BoringCache with your current cache.
Send a repo and a workflow. Get paired measurements on your runner class in 48 hours after I confirm the setup.
Set up BoringCache
Install the CLI, connect your repository, and choose what to cache.
curl -sSL https://install.boringcache.com/install.sh | sh cd your-project boringcache onboard