Infrastructure / Storage & Retrieval

OpenLake

OpenLake is a distributed storage engine for LLM inference and GPU training, built in Rust on io_uring and aimed at small-I/O throughput and sub-millisecond reads. Two surfaces sit on the same engine: an offload pool that spills KV cache off GPU nodes, and a petabyte-scale S3-compatible object store. A vLLM connector ships in the repository.

Verified 2026-08-18 via the GitHub API and the LICENSE body.

Openness

5 high confidence

5.0

license: Apache-2.0(OSI)
source: public
core-gated: ungated

Apache-2.0 license body confirmed. The repository is public and unarchived and builds the whole product, and the README describes no paid tier, enterprise edition or license-gated build beside it, so source is public and the core ungated.

https://github.com/openlake-project/openlake/blob/main/LICENSE recorded 2026-08-18
LICENSE file is the verbatim Apache-2.0 text
https://api.github.com/repos/openlake-project/openlake recorded 2026-08-18
Repo metadata - license spdx_id Apache-2.0, private false, archived false, default branch main - for openlake-project/openlake.
https://github.com/openlake-project/openlake/blob/main/README.md recorded 2026-08-18
README describes distributed storage for GPU workloads built in Rust on io_uring, presenting a KV-cache offload pool and a petabyte-scale S3-compatible object store, with published throughput and latency figures and a vLLM connector, with no paid tier, enterprise edition or license-key-gated build beside it.

Adoption

2 low confidence

2.0

2,330 GitHub stars, which lands in the 1K-10K stars band of the stars scale, level 2. Built from source or run from container images and Helm charts, with no package registry channel, so the stars scale applies; at 2,330 stars the band is 2.

https://api.github.com/repos/openlake-project/openlake recorded 2026-08-18
Repo metadata - stargazers_count = 2,330 - for openlake-project/openlake.

Capability

3 medium confidence

3.0

Banded on the category feature matrix as single-purpose store or index. Placed two bands below the vespa anchor, on a matrix that bands on how much of the persist-index-retrieve path a product provides itself, at what scale and over how many retrieval modes.

https://github.com/openlake-project/openlake/blob/main/README.md recorded 2026-08-18
README still documents distributed storage for GPU workloads built in Rust on io_uring, presenting a KV-cache offload pool and a petabyte-scale S3-compatible object store, with published throughput and latency figures and a vLLM connector.

Verified 2026-08-18