Release Notes

July 30, 2026

v0.0.99

NemoClaw v0.0.99 strengthens snapshot restore, sandbox recovery, shared-route upgrades, Hermes lockdown, and experimental runtime identity. It also hardens host readiness, inference health checks, managed images, documentation routing, and release end-to-end (E2E) evidence.

  • Snapshot restore can now create a Docker- or VM-driver replacement from a stopped source when the registry records its image and complete inference route. Restored SQLite databases must accept a write transaction, and OpenClaw clone restore waits for bounded managed-supervisor readiness before it applies state. Pairing verification now proves that the restored authenticated session belongs to the clone. For more information, refer to Create and Restore Snapshots and the NemoClaw CLI Commands Reference.
  • Legacy supervisor recovery now backs up manifest-declared state before it recreates a container and restores that state only after replacement identity and managed health pass. Rebuild recovery manifests publish atomically, OpenClaw onboarding persists the credential-free nemoclaw-start command, and recreated managed OpenClaw configuration files regain their required writable mode. Failed recovery preserves the temporary backup and reports host recovery guidance when rollback also fails. For more information, refer to Recover and Rebuild Sandboxes and the NemoClaw CLI Commands Reference.
  • Rebuild now migrates only missing canonical credential environment-variable names for legacy sandboxes that share a gateway route. It revalidates the target and every registered peer immediately before deletion, while explicit credential, model, endpoint, API-family, and gateway conflicts continue to stop the rebuild. For more information, refer to Use Shared Gateway Routes and the NemoClaw CLI Commands Reference.
  • Hermes lockdown now keeps /sandbox/.hermes at 3770 root:sandbox, which lets the gateway create runtime state while sealed configuration files remain protected. Gateway restart, recovery, and connect now classify exhausted or refused relaunches as relaunch quarantined and direct you to rebuild instead of retrying a deterministic refusal. For more information, refer to Troubleshooting and the NemoClaw CLI Commands Reference.
  • The experimental direct OpenClaw blueprint runner now includes a data-only Microsoft Entra runtime identity reference. The reviewed policy restricts refresh to login.microsoftonline.com, bearer delivery to GET graph.microsoft.com/v1.0/me, and delegated permission guidance to User.Read with offline_access. NemoClaw does not package OAuth bootstrap, on-behalf-of exchange, or a production identity middleware service, and normal nemoclaw onboard does not enable this component. For more information, refer to Configure Experimental Runtime Identity.
  • nemoclaw host probe now classifies a symlinked DGX Station release marker as unqualified instead of inconclusive, matching the other rejected marker shapes. Local inference adapter health checks now retain at most 64 KiB and fail closed on oversized declared or chunked loopback responses. For more information, refer to System Readiness.
  • Managed Hermes images now pin Node.js 24.18.1, uv==0.11.33, mcp==1.28.1, and tornado==6.5.7. Managed LangChain Deep Agents Code images retain the reviewed 0.1.34 integration contract while pinning uv==0.11.33, mcp==1.28.1, Pillow==12.3.0, and pyasn1==0.6.4. Image validation also rejects retained uv build cache metadata, ignores build-only BuildKit telemetry during the Deep Agents Code probe, and clears each local platform pull before validating the next architecture.
  • Trusted CI now publishes agent-complete Open Container Initiative images by immutable digest, validates anonymous pulls and runtime contracts, and promotes aliases only after those checks pass. Dormant managed-image selection and startup-profile contracts resolve exact all-agent cohorts and bounded agent-specific startup data without activating buildless onboarding or changing the current Dockerfile path.
  • Documentation now keeps provider-switch sections within the applicable OpenClaw and Hermes guide variants, corrects the Omni sub-agent model ID, and generalizes agent-selection guidance. The contributor workflow also separates pre-tag release entries from post-tag Announcements and corrects the NVIDIA DORI installation pin from 0.10.0 to 0.9.0. For more information, refer to Switch Inference Providers and Set Up Task-Specific Sub-Agents.
  • Release E2E now preserves command and agent first-turn latency separately, evaluates recurring anomalies within an exact 12-sample cohort, and routes retired rebuild selectors to focused replacement evidence. The credential-generation window runs independently, managed startup recovery covers the persisted startup command, and the standing Brev Launchable waits for the staging image family before deployment.