Sonar

license

AGPL-3.0(OSI)

source

public(the published repository is the engine)

core-gated

ungated(no enterprise path in the repository root and no paid build of the engine in the README)

The LICENSE body is the AGPL-3.0 text, read in full rather than taken from the API's label, and carries no appended condition. The repository is public and unarchived and builds the engine itself. Its root tree carries no enterprise, ee or commercial directory and its README describes no licence-gated build, so the core reads as ungated. Confidence is medium because that is a repository-and-README read rather than a pricing-page read.

• https://raw.githubusercontent.com/dphnAI/sonar/main/LICENSE recorded 2026-08-31

  LICENSE body, read in full: the stock GNU AGPL-3.0 text, with only template placeholders in its appendix and no appended condition.

• https://api.github.com/repos/dphnAI/sonar recorded 2026-08-31

  Repo metadata for dphnAI/sonar - archived false, 1,844 stars.

• https://raw.githubusercontent.com/dphnAI/sonar/main/README.md recorded 2026-08-31

  README, read for a paid tier, an enterprise edition or a licence-gated build beside the published source, and for whether any component is stated to be private.

1,844 GitHub stars, which lands in the 1K-10K stars band of the stars scale, where the scale caps at 3. No package artifact is declared for this record, so stars are the only instrument available and the band should be read as a floor.

• https://api.github.com/repos/dphnAI/sonar recorded 2026-08-31

  Repo metadata - stargazers_count = 1,844 - for dphnAI/sonar.

One band below the vllm anchor rather than level with it. The feature list matches the anchor's closely, but Sonar is a fork of it, so the capability is inherited rather than independently established - and sglang holds the `at` band on a record of its own.

• https://raw.githubusercontent.com/dphnAI/sonar/main/README.md recorded 2026-08-31

  README, read for the engine's feature set: Continuous batching, paged KV-cache management, optimized kernels, quantization, speculative decoding and distributed serving over Hugging Face-compatible models.