Release Notes

v0.0.93

NemoClaw v0.0.93 updates DGX Station and DGX Spark onboarding, adds resumable managed vLLM download guidance, preserves installer cancellation status, rejects Intel macOS before downloads, and strengthens release validation.

• DGX Station Express now recognizes the stock no-OTA DGX OS 7.6.x workstation family when its release marker proves the expected GB300 lineage. The existing hardware, driver, ECC, Docker, CDI, and container GPU checks still apply, and future release families remain fail-closed. Stock DGX OS and AI Developer Tools profiles can keep an idle PackageKit daemon because those paths preserve factory packages, but active or malformed package transactions still block preparation. Full Station Express end-to-end qualification for the accepted no-OTA DGX OS 7.6.x profile remains pending. For more information, refer to Prepare DGX Station to Install NemoClaw and Platform Support and Launch Claims.
• When Station Express detects an existing vLLM workload, NemoClaw leaves the workload unchanged and reports an exact manual stop command. The default choice preserves the managed Express recipe and prints an exact revision-pinned resume command. The alternative keeps the running vLLM and continues through advanced manual Local vLLM setup while preserving the selected installer revision and ports across a login handoff or interrupted retry. A non-interactive run preserves Express and does not change the host. For more information, refer to Prepare DGX Station to Install NemoClaw and the NemoClaw Quickstart with OpenClaw.
• Managed vLLM onboarding now explains optional Hugging Face read-token authentication before large public-model downloads. NemoClaw passes the token only to the temporary downloader, sanitizes downloader output across standard output and standard error, and prints resumable HTTP 429 recovery steps that reuse the existing cache. On DGX Spark, non-interactive onboarding with no requested or recorded provider now selects a running local vLLM first, then managed vLLM, and then NVIDIA Endpoints when neither local option is available. DGX Station and other hosts keep their existing unset-provider behavior. For more information, refer to Set Up vLLM and the NemoClaw Quickstart with OpenClaw.
• The public installer now rejects Intel macOS before it resolves a release reference or performs network work, and it reports that macOS requires Apple Silicon. Pressing Ctrl+C at a hidden onboarding credential prompt now preserves exit status 130 and resumable-session guidance without printing the rejected prompt error or a Node.js stack. For more information, refer to Platform Support and Launch Claims and the NemoClaw CLI Commands Reference.
• Release validation now waits for the relevant base image before final-main E2E fanout, tests the staging Brev Launchable, centralizes larger-runner selection, and retries one confirmed hosted-runner loss. E2E runs also publish semantic phase durations and runner-comparison telemetry while ignoring base-image run history that cannot affect the candidate. These controls separate infrastructure loss from product failures and keep candidate validation tied to the image under test.
• Documentation checks now require a documentation-writer receipt for docs-only PRs and record the matching PR without redundant receipt metadata. Quickstart platform guidance and inference command references now match the supported CLI paths, and the historical v0.0.91 audit follow-up remains part of the canonical changelog.