> This page is for version Latest (default).
> For other versions, use one of these documentation indexes:
> - Latest (default): https://docs.nvidia.com/nemoclaw/latest/llms.txt

> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemoclaw/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemoclaw/_mcp/server.

## v0.0.108

NemoClaw v0.0.108 adds read-only host mounts and an Experimental Muse Glimmer profile for one DGX Spark.
It improves onboarding recovery, messaging credential rotation, inference validation, MCP registration, snapshots, and Hermes configuration.
It also strengthens managed images, gateway credentials, runtime state, and release qualification.

* On Linux and Windows Subsystem for Linux 2 (WSL2), `nemoclaw onboard --host-mount <host:/sandbox/path>` can now expose an existing host directory read-only beneath `/sandbox`.
  NemoClaw validates each source, destination, and symlink boundary before mutation.
  It persists accepted mounts across `nemoclaw <sandbox> rebuild` and interrupted onboarding resumed with `nemoclaw onboard --resume`.
  The `nemoclaw <sandbox> destroy` command removes their declaration.
  The `nemoclaw <sandbox> status` command reports them.
  For more information, refer to [Understand Sandbox State](/user-guide/openclaw/manage-sandboxes/state-and-backups/understand-sandbox-state) and the [NemoClaw CLI Commands Reference](/user-guide/openclaw/reference/commands).
  Related change: [PR #8280](https://github.com/NVIDIA/NemoClaw/pull/8280).
* The explicit-only Experimental Muse Glimmer managed vLLM profile now runs on one DGX Spark with its validated checkpoint, ARM64 image, parser settings, and resource limits.
  Two-node DGX Spark setup can remediate a Docker storage conflict before launch only when it is the sole blocking readiness finding and the host reports that remediation is available, and strict tool-call validation escalates its bounded token budget through 256, 1,024, and 4,096 tokens before reporting failure.
  NVIDIA Nemotron 3.5 Lightning guidance also distinguishes the `reasoning` and `max_tokens` fields required by direct OpenAI-compatible callers.
  For more information, refer to [Set Up vLLM](/user-guide/openclaw/inference/local-inference/set-up-vllm), [Set Up vLLM on Two DGX Sparks](/user-guide/openclaw/inference/local-inference/set-up-vllm-on-two-dgx-sparks), and [Understand Provider Validation](/user-guide/openclaw/inference/validate-inference/understand-provider-validation).
  Related changes: [PR #8802](https://github.com/NVIDIA/NemoClaw/pull/8802), [PR #8814](https://github.com/NVIDIA/NemoClaw/pull/8814), [PR #8839](https://github.com/NVIDIA/NemoClaw/pull/8839), and [PR #8894](https://github.com/NVIDIA/NemoClaw/pull/8894).
* Onboarding recovery now preserves the selected configuration after review, hides suggestions for incomplete route-only sandboxes, and keeps an already healthy Docker authority.
  Explicit fresh recreation, repeated Docker recreation, dashboard port reservation, unavailable-provider guidance, decorated OpenShell readiness output, and readiness handoffs now converge through the same bounded lifecycle authority.
  The recovery path also handles registered messaging routes, empty dashboard URLs, managed runtime ownership, OpenClaw MCP workspace state, and LangChain Deep Agents Code re-onboarding verification without masking terminal failures.
  For more information, refer to [Recover and Rebuild Sandboxes](/user-guide/openclaw/manage-sandboxes/operate-sandboxes/recover-and-rebuild-sandboxes), [System Readiness](/user-guide/openclaw/reference/system-readiness), and [Troubleshooting](/user-guide/openclaw/reference/troubleshooting).
  Related changes: [PR #8724](https://github.com/NVIDIA/NemoClaw/pull/8724), [PR #8820](https://github.com/NVIDIA/NemoClaw/pull/8820), [PR #8823](https://github.com/NVIDIA/NemoClaw/pull/8823), [PR #8842](https://github.com/NVIDIA/NemoClaw/pull/8842), [PR #8851](https://github.com/NVIDIA/NemoClaw/pull/8851), [PR #8863](https://github.com/NVIDIA/NemoClaw/pull/8863), [PR #8901](https://github.com/NVIDIA/NemoClaw/pull/8901), [PR #8929](https://github.com/NVIDIA/NemoClaw/pull/8929), and [PR #8931](https://github.com/NVIDIA/NemoClaw/pull/8931).
* Messaging credential changes now rebuild the sandbox when durable gateway registration no longer matches the reviewed selection.
  Compact persisted authority is compared without exposing credentials, and ambiguous or failed gateway reads remain terminal instead of being treated as an absent registration.
  For more information, refer to [Credential Rotation](/user-guide/openclaw/security/credential-rotation) and [Manage Messaging Channels](/user-guide/openclaw/manage-sandboxes/messaging-channels/manage-messaging-channels).
  Related changes: [PR #8859](https://github.com/NVIDIA/NemoClaw/pull/8859) and [PR #8939](https://github.com/NVIDIA/NemoClaw/pull/8939).
* Managed Model Context Protocol (MCP) registration now targets the OpenClaw workspace configuration, while agent dispatch exits nonzero when a turn does not produce a delivered response.
  Incomplete-turn markers, gateway selection, and non-interactive execution are preserved so scripts do not receive false success.
  For more information, refer to [Manage MCP Servers](/user-guide/openclaw/manage-sandboxes/mcp-servers/manage-mcp-servers) and the [NemoClaw CLI Commands Reference](/user-guide/openclaw/reference/commands).
  Related changes: [PR #8646](https://github.com/NVIDIA/NemoClaw/pull/8646), [PR #8846](https://github.com/NVIDIA/NemoClaw/pull/8846), and [PR #8857](https://github.com/NVIDIA/NemoClaw/pull/8857).
* Hermes configuration writes now validate the complete candidate configuration, require explicit approval for private service URLs, and restart only after the accepted state is durable.
  Snapshot clones preserve their allocated gateway port so the restored sandbox and registry agree before startup.
  For more information, refer to the [Hermes Quickstart](/user-guide/hermes/get-started/quickstart), [Create and Restore Snapshots](/user-guide/openclaw/manage-sandboxes/state-and-backups/create-and-restore-snapshots), and [Troubleshooting](/user-guide/hermes/reference/troubleshooting).
  Related changes: [PR #8845](https://github.com/NVIDIA/NemoClaw/pull/8845) and [PR #8907](https://github.com/NVIDIA/NemoClaw/pull/8907).
* Legacy OpenShell gateway replacement now retires only verified managed state, corporate CA staging preserves trusted ownership, and Shields state remains readable after runtime locking.
  NemoClaw creates managed state with owner-only permissions, strips the gateway token from descendant processes, and preserves authenticated gateway metadata through sandbox launch.
  For more information, refer to [Configure Corporate CA Trust](/user-guide/openclaw/security/configure-corporate-ca-trust), [Gateway and Secret Controls](/user-guide/openclaw/security/security-controls/gateway-authentication-controls), and [Credential Storage](/user-guide/openclaw/security/credential-storage).
  Related changes: [PR #8811](https://github.com/NVIDIA/NemoClaw/pull/8811), [PR #8812](https://github.com/NVIDIA/NemoClaw/pull/8812), [PR #8822](https://github.com/NVIDIA/NemoClaw/pull/8822), [PR #8860](https://github.com/NVIDIA/NemoClaw/pull/8860), [PR #8872](https://github.com/NVIDIA/NemoClaw/pull/8872), and [PR #8921](https://github.com/NVIDIA/NemoClaw/pull/8921).
* Managed images now use Node.js 22.23.2, updated runtime dependencies, an audited Hono lock, and `setpriv` instead of legacy `gosu` privilege transitions.
  BuildKit attestation verification is part of image validation, while Sigstore auditing runs outside image builds and the Hermes sandbox base is pinned to the refreshed reviewed digest.
  For more information, refer to [Process Controls](/user-guide/openclaw/security/security-controls/process-controls), [Trusted Computing Base](/user-guide/openclaw/security/trusted-computing-base), and [Update Sandboxes](/user-guide/openclaw/manage-sandboxes/operate-sandboxes/update-sandboxes).
  Related changes: [PR #8819](https://github.com/NVIDIA/NemoClaw/pull/8819), [PR #8858](https://github.com/NVIDIA/NemoClaw/pull/8858), [PR #8862](https://github.com/NVIDIA/NemoClaw/pull/8862), [PR #8864](https://github.com/NVIDIA/NemoClaw/pull/8864), [PR #8914](https://github.com/NVIDIA/NemoClaw/pull/8914), [PR #8927](https://github.com/NVIDIA/NemoClaw/pull/8927), and [PR #8928](https://github.com/NVIDIA/NemoClaw/pull/8928).
* Contributor guidance now covers JavaScript heap exhaustion during setup, required macOS command-line dependencies, byte-asserted line endings, and the v0.0.106 audit follow-ups.
  For more information, refer to the [documentation contribution guide](https://github.com/NVIDIA/NemoClaw/blob/main/docs/CONTRIBUTING.md) and [Troubleshooting](/user-guide/openclaw/reference/troubleshooting).
  Related changes: [PR #8689](https://github.com/NVIDIA/NemoClaw/pull/8689), [PR #8700](https://github.com/NVIDIA/NemoClaw/pull/8700), [PR #8779](https://github.com/NVIDIA/NemoClaw/pull/8779), and [PR #8831](https://github.com/NVIDIA/NemoClaw/pull/8831).
* Release qualification now reports one consolidated result across required end-to-end jobs, lifecycle integration coverage shares isolated host-process scenarios, and qualification checks share one dotted-version comparator.
  NemoClaw no longer contains the Jetson dispatch backend and retains controller contract coverage.
  The release train also adds deterministic recovery fixtures, bounded SSH and preflight waits, formatted Hermes diagnostics, centralized onboarding wiring, and runtime-aligned live probes.
  Related changes: [PR #8780](https://github.com/NVIDIA/NemoClaw/pull/8780), [PR #8840](https://github.com/NVIDIA/NemoClaw/pull/8840), [PR #8841](https://github.com/NVIDIA/NemoClaw/pull/8841), [PR #8843](https://github.com/NVIDIA/NemoClaw/pull/8843), [PR #8850](https://github.com/NVIDIA/NemoClaw/pull/8850), [PR #8854](https://github.com/NVIDIA/NemoClaw/pull/8854), [PR #8861](https://github.com/NVIDIA/NemoClaw/pull/8861), [PR #8871](https://github.com/NVIDIA/NemoClaw/pull/8871), [PR #8874](https://github.com/NVIDIA/NemoClaw/pull/8874), [PR #8875](https://github.com/NVIDIA/NemoClaw/pull/8875), [PR #8881](https://github.com/NVIDIA/NemoClaw/pull/8881), [PR #8899](https://github.com/NVIDIA/NemoClaw/pull/8899), [PR #8905](https://github.com/NVIDIA/NemoClaw/pull/8905), [PR #8906](https://github.com/NVIDIA/NemoClaw/pull/8906), [PR #8909](https://github.com/NVIDIA/NemoClaw/pull/8909), [PR #8911](https://github.com/NVIDIA/NemoClaw/pull/8911), and [PR #8932](https://github.com/NVIDIA/NemoClaw/pull/8932).