Developer docs
Publish reproducible compute repositories and benchmark runs with a kovara.yaml manifest and the kovara CLI.
Guides
Benchmark method
kovara benchmark measures your own OpenAI-compatible endpoint. Kovara runs nothing on its side: no GPUs, no inference, no execution of manifests. This page explains exactly what the CLI measures, how, and what it does not.
The kovara CLI
kovara is the open-source (Apache-2.0) command line for compute repositories: write and validate kovara.yaml, benchmark an OpenAI-compatible endpoint, publish manifests and runs, and pull published manifests. Source: packages/kovara-cli/.
Evidence states and comparability
A benchmark run on Kovara is a claim: "this workload, on this hardware, under these conditions, measured these numbers." Kovara shows every run with how much it can be trusted, and never mixes runs that cannot be compared.
kovara.yaml — workload manifest specification (schema_version "1")
A kovara.yaml describes one AI workload so that someone else can run it again: which model (and which commit of it), which runtime engine and version, which accelerator and how many, which precision and parallelism, and the default benchmar
Publishing manifests and benchmark runs
The CLI shows the JSON it will send and asks before sending. The server validates it again (the same rules, plus: the accelerator must be a GPU in Kovara's catalogue), computes the canonical JSON and SHA-256, and stores an immutable version