Release Notes

NemoClaw v0.0.115 strengthens Portable Hermes recovery, sandbox lifecycle authority, managed messaging credentials, and installer recovery. It also improves managed local inference and adds bounded experimental planning for an externally managed OpenShell target.

• Portable Hermes recovery now revalidates the exact receipt-owned Podman container, OpenShell gateway, executable, policy, route, and runtime identities before each operation. If recovery starts a stopped receipt-owned container and authenticated Hermes health remains unavailable, it launches the receipt-recorded nemoclaw-start command once and waits for authenticated health. If the container was already running, recovery only waits for authenticated health and does not launch another startup process. A failed recovery rolls back only the exact container that recovery started. Related changes: PR #10315, PR #10376, PR #10441, PR #10456, and PR #10499.
• Stock Docker-driver onboarding for OpenClaw, Hermes, and LangChain Deep Agents Code now requires the release’s exact managed image. Registry or catalog failures stop before sandbox creation instead of falling back to a local stock-image build; explicit custom Dockerfiles remain separate. Existing and recreated sandboxes retain exact image, policy, route-reservation, and lifecycle authority checks. Related changes: PR #10113, PR #10320, PR #10321, PR #10322, PR #10332, PR #10396, and PR #10422.
• Messaging setup now binds revision-scoped credentials to canonical OpenShell providers before sandbox creation or rebuild. This restores runtime credential delivery for maintained Slack, Discord, Google Chat, and Telegram paths while preserving endpoint-specific policy matching and fail-closed provider ownership. Related changes: PR #10170, PR #10271, PR #10273, PR #10275, PR #10277, PR #10307, and PR #10314.
• The Hermes installer accepts --defer-onboarding or NEMOCLAW_DEFER_ONBOARDING=1 only for NVIDIA-hosted inference when no supported credential and no sandbox exist. It installs NemoClaw and Hermes without creating a provider, sandbox, or completed onboarding state; any credential or existing sandbox keeps the normal validation and recovery path. Related change: PR #10299.
• The experimental managed llama.cpp path now offers NVIDIA Nemotron 3 Nano 30B-A3B on qualified DGX Spark Arm64 and Linux x86_64 NVIDIA GPU hosts and recommends it during onboarding. Meta Muse Glimmer remains available on DGX Spark only by explicit selection, and existing Muse-owned installations are not migrated. Local NVIDIA NIM selection now enforces the documented usable-memory limit, including the DGX Spark unified-memory cap. Related changes: PR #10122 and PR #10292.
• nemoclaw upgrade-sandboxes --check now exits nonzero when it reports actionable stale, unknown-version, backup-recovery, or missing-sandbox state. Sandbox destruction and stale-container cleanup have bounded waits and preserve registry or lifecycle authority when deletion cannot be confirmed. Non-portable managed Hermes uninstall also removes its exact owned state volume and stops before state retirement on Docker failure. Related changes: PR #10128, PR #10133, and PR #10224.
• The experimental direct blueprint runner can validate and sanitize a plan for an externally managed OpenShell target. Planning validates the HTTPS endpoint, workspace, expected release range, CA bundle, and authentication-file metadata without reading credential contents, connecting to the gateway, authenticating, or applying changes. Related change: PR #10045.
• Security and diagnostics now reject config reads through a symlinked config directory, redact URL userinfo credentials in debug bundles, bind sandbox mutations and cancellation recovery to durable exact identity, and classify incomplete onboarding without reporting success. Related changes: PR #10041, PR #10127, PR #10146, and PR #10396.

NemoClaw v0.0.114 adds deterministic read-only MCP tool calls for LangChain Deep Agents Code and per-stage launch-readiness probe timing. It strengthens destructive-operation warnings, session export cleanup, sealed configuration recovery, and installation verification. It also improves managed local inference, Portable and Hermes onboarding, image provenance, and release documentation automation.

NemoClaw v0.0.113 improves sandbox and onboarding recovery across interactive connections, Hermes, Portable, policy changes, and local adapters. It adds experimental Hermes Google Chat support while keeping the service-account private key outside the sandbox. It also changes the Google Gemini default, strengthens managed image publication, and improves E2E diagnostics.

NemoClaw v0.0.112 strengthens managed local inference across vLLM, llama.cpp, Ollama, and routed provider recovery. It improves Portable and sandbox lifecycle recovery, MCP credential republishing, messaging continuity, and Shields ownership cleanup. It also tightens release provenance, E2E qualification, contributor review automation, and dependency compatibility.

NemoClaw v0.0.111 extends the explicit experimental Portable profile with receipt-owned Hermes lifecycle authority and a fixed host-gateway and registry network topology. It makes Shields recovery, sandbox rebuilds, provider routing, and messaging bootstrap more diagnosable and less likely to leave ambiguous state. It also improves headless and local-inference onboarding, managed gateway recovery, uninstall cleanup, and release qualification.

NemoClaw v0.0.110 adds an Experimental managed llama.cpp profile for Meta Muse Glimmer 30B on one DGX Spark and requires native tool-use evidence from custom Anthropic-compatible endpoints. It strengthens the explicit experimental Portable OpenClaw path with rootless Podman lifecycle authority, CPU-delegation preflight, and receipt-bound uninstall. It also improves onboarding recovery, local inference diagnostics, messaging and policy cleanup, backup and uninstall safety, and release qualification.

NemoClaw v0.0.109 adds credential-free launch-readiness leases, an editable onboarding review, a distinct OpenAI-compatible API port for each Hermes sandbox, and selectable Hermes WhatsApp reply modes. It also adds a Deferred N1x Express preview for one-host managed vLLM while N1x remains outside the supported-platform set. It improves inference health reporting, local inference discovery, onboarding recovery, sandbox startup, messaging status, and uninstall behavior. It also strengthens managed images, Deep Agents Code login probes, Shields transitions, gateway lifecycle authority, and release qualification.

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 and the NemoClaw CLI Commands Reference. Related change: PR #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, Set Up vLLM on Two DGX Sparks, and Understand Provider Validation. Related changes: PR #8802, PR #8814, PR #8839, and PR #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, System Readiness, and Troubleshooting. Related changes: PR #8724, PR #8820, PR #8823, PR #8842, PR #8851, PR #8863, PR #8901, PR #8929, and PR #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 and Manage Messaging Channels. Related changes: PR #8859 and PR #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 and the NemoClaw CLI Commands Reference. Related changes: PR #8646, PR #8846, and PR #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, Create and Restore Snapshots, and Troubleshooting. Related changes: PR #8845 and PR #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, Gateway and Secret Controls, and Credential Storage. Related changes: PR #8811, PR #8812, PR #8822, PR #8860, PR #8872, and PR #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, Trusted Computing Base, and Update Sandboxes. Related changes: PR #8819, PR #8858, PR #8862, PR #8864, PR #8914, PR #8927, and PR #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 and Troubleshooting. Related changes: PR #8689, PR #8700, PR #8779, and PR #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, PR #8840, PR #8841, PR #8843, PR #8850, PR #8854, PR #8861, PR #8871, PR #8874, PR #8875, PR #8881, PR #8899, PR #8905, PR #8906, PR #8909, PR #8911, and PR #8932.

NemoClaw v0.0.107 adds an Experimental NVIDIA Nemotron 3.5 Lightning profile for one DGX Spark and awaitable Slack readiness for automation. It improves cold-start onboarding, dashboard forwarding, Windows-host Ollama, Hermes operations, sandbox recovery, and CLI inventory output. It also strengthens Hermes Shields state changes and removes sensitive values from more diagnostics.

NemoClaw v0.0.106 converges readiness across lifecycle commands, upgrades the managed OpenShell runtime to v0.0.101, and adds bounded DGX Spark vLLM choices. It strengthens sandbox and Hermes recovery, local inference diagnostics, endpoint policy authority, and scoped uninstall. It also improves update safety, image defaults, and installation failure reporting.

NemoClaw v0.0.105 restores local and managed inference paths across Windows, Linux ARM64, DGX Spark, Ollama, vLLM, and managed llama.cpp. It also improves Shields recovery, uninstall ownership, Hermes operations, network-policy feedback, remote dashboard guidance, agent output integrity, and cold container compatibility probing.

• Strict local-provider validation now retries one reasoning-only tool-call truncation with a larger token budget and still fails unless the retry returns a structured tool call. vLLM parser errors now identify the required automatic tool-choice and parser settings, while Windows-host Ollama readiness runs from the Docker Desktop network context that reaches host.docker.internal. For more information, refer to Understand Provider Validation, Use Ollama, and Additional Setup for Windows Machines.
• Managed vLLM onboarding now accepts its authenticated loopback endpoint without requiring an unrelated trusted-private capability. Dual DGX Spark discovery accepts the filtered ip neighbor output produced by the host and names the failed rail check, while eligible native Linux ARM64 hosts can prove denylisted GPU names with the bounded Docker CUDA workload. The experimental managed llama.cpp lifecycle also uses the exact loopback port declared by its selected recipe. For more information, refer to Set Up vLLM, Set Up vLLM on Two DGX Sparks, and Troubleshooting.
• Shields down can now recover an OpenClaw sandbox whose protected startup failed before readiness, but only after the installed guard proves that no startup child or readiness lease remains. Hermes Shields transitions now wait for the trusted inference route to converge and roll back the existing transaction when the bounded route check fails. For more information, refer to Understand Runtime Changes, Recover and Rebuild Sandboxes, and Security Best Practices.
• Full uninstall no longer matches unrelated Docker containers and images whose names contain openclaw. It leaves resources from a separate OpenClaw installation in place while continuing to remove the Docker resources that NemoClaw identifies as its own. For more information, refer to Uninstall NemoClaw.
• Hermes now keeps legacy dashboard startup inside its prepared, privilege-separated profile and avoids unintended re-execution into the machine-level dashboard. The nemohermes <sandbox> sessions delete <id> command also uses in-memory SQLite temporary storage so session deletion works inside the restricted sandbox process context. For more information, refer to the NemoClaw CLI Commands Reference and Troubleshooting.
• An interactive policy restore refusal now reports Cancelled., and a non-interactive refusal prints the complete usage line. Both refusal paths stop before policy mutation. For more information, refer to Network Policies Reference and the NemoClaw CLI Commands Reference.
• When an SSH operator needs a port forward for a running OpenClaw or Hermes dashboard, status now points to the tokenized URL from dashboard-url. The hint remains absent for non-SSH sessions, stopped gateways, routable dashboards, and Deep Agents Code sandboxes. For more information, refer to Deploy to a Headless Server and the NemoClaw CLI Commands Reference.
• OpenClaw message handling now reconciles cumulative assistant snapshots with delta and replacement events before it publishes the final response. This recovers text from later snapshots without duplicating earlier output and uses the pinned headless loopback client identity accepted by OpenClaw v2026.7.1.
• Managed Deep Agents Code requests for the reviewed Nemotron Ultra model IDs now include the fixed nonempty-content template argument without trusting mutable provider parameters. A successful Deep Agents Code skill installation also prints its confirmed SHA-256 content digest so operators can compare later installations. For more information, refer to the NemoClaw CLI Commands Reference and Run LangChain Deep Agents Code.

NemoClaw v0.0.104 adds an experimental managed llama.cpp option for DGX Spark, trusted private endpoint configuration, and a selectable Personal network policy tier. It makes agent manifests authoritative for persistent state and strengthens gateway, rebuild, registry, and uninstall recovery. It also improves Hermes configuration safety, MCP diagnostics, credential isolation, and host installation guidance.

NemoClaw v0.0.103 adds nemoclaw launch <name> and its agent-specific CLI variants so you can start an agent directly after the standard sandbox preflight and recovery checks. It improves onboarding, managed inference, installation, uninstall, snapshot, rebuild, and Shields failure handling with more accurate recovery behavior and diagnostics. It also strengthens endpoint validation, sandbox privilege separation, and the managed Hermes and LangChain Deep Agents Code lifecycle.

NemoClaw v0.0.102 adds authenticated attachment of operator-managed llama.cpp servers and an Experimental managed vLLM profile for two DGX Spark systems. It also improves DGX Station and Windows installation, gateway and sandbox recovery, Shields transactions, inference reliability, multi-port uninstall, and Hermes and LangChain Deep Agents Code workflows. It reduces the managed single-node DGX Spark Qwen profile’s default memory demand during long-context agent workflows.

NemoClaw v0.0.101 adds experimental Google Chat support for OpenClaw and improves runtime status, failed-gateway cleanup, inference-route cleanup, backup handling, and preservation of Hermes home-channel assignments during rebuilds. It also strengthens backup sanitization, lays dormant provider-neutral foundations for managed workload replacement, and expands trusted review and end-to-end (E2E) coverage.

NemoClaw v0.0.100 strengthens restored OpenClaw pairing, transactional sandbox replacement, managed Deep Agents Code, and host readiness provenance. It also improves onboarding recovery, lifecycle cleanup, Hermes image builds, runtime diagnostics, documentation, and trusted end-to-end (E2E) evidence.

• OpenClaw cross-sandbox restore now uses descriptor-pinned clone pairing, while fresh onboarding continues to use generated pairing identity. A restored clone can perform one bounded scope-upgrade recovery and tolerate a brief pending-request publication interval. Unsafe filesystem shapes, persistent malformed state, and mismatched identities still fail closed. For more information, refer to Create and Restore Snapshots.
• Managed Model Context Protocol (MCP) startup for Deep Agents Code now works when OpenShell seccomp denies memfd_create and workspace-backed /tmp rejects O_TMPFILE. The Deep Agents Code sandbox receives a 1 MiB private tmpfs with verified mount options, and the managed runtime keeps its anonymous descriptor and integrity checks. For more information, refer to Run LangChain Deep Agents Code.
• Managed Deep Agents Code requests now apply the recorded compatible-endpoint reasoning effort at runtime. Recovered onboarding and sandbox recreation also preserve recorded reasoning mode and effort instead of accepting unrelated ambient values. For more information, refer to Quickstart with Deep Agents and Configure Model Capabilities.
• rebuild and same-name onboarding replacement now record a transaction before the first destructive mutation. Recovery binds the source, replacement, registry generation, and OpenShell gateway, then continues the recorded operation or fails closed when those identities drift. After the registry proves the replacement identity and generation, NemoClaw removes an obsolete owned source image unless the source is shared or the replacement reuses it. For more information, refer to Recover and Rebuild Sandboxes and the NemoClaw CLI Commands Reference.
• Compatible-endpoint onboarding now limits the Responses API streaming-event probe to 5 seconds while preserving the Chat Completions API fallback. Onboarding reuses a successful Chat Completions validation result instead of sending the immediate host-side validation request when the public endpoint, model, authentication mode, and request requirements match. The validated IP address set must also match, so onboarding sends another validation request after the DNS pin changes. NemoClaw still sends a separate validation request for an operator-trusted private endpoint. Final in-sandbox route verification for OpenClaw and Hermes now requires inference.local to return an HTTP response within 2 seconds per attempt, which leaves client overhead before OpenClaw’s 2.5-second provider preflight limit. Host interruptions during an active onboarding step produce the existing resumable recovery path instead of an invalid state transition. DGX Station Express also preserves its owner-only resume receipt when automatic dual-Station discovery selects the single-Station fallback. For more information, refer to Choose a Compatible Inference API, Quickstart, and Prepare DGX Station to Install NemoClaw.
• nemoclaw status now reads terminal-runtime out-of-memory counters through a bounded host-side Docker probe, so a recorded kill produces degraded status and rebuild guidance. Destroying the final sandbox now stops a packaged OpenShell gateway service and refuses cleanup when the service remains active. For more information, refer to the NemoClaw CLI Commands Reference and Troubleshooting.
• shields down now succeeds without changing state when an OpenClaw configuration already has the exact mutable posture. Cloudflare Tunnel cleanup verifies that the recorded process still belongs to cloudflared before each signal and removes a stale PID file without signaling an unrelated process. For more information, refer to Understand Runtime Changes and Run Sandboxes.
• Managed Hermes image probes now run through a checked-in Python runner, so OpenShell gateways that use Docker’s legacy builder enforce the same image assertions as BuildKit. For more information, refer to Install Hermes Plugins.
• nemoclaw host probe schema 1.1.0 now identifies the exact compiled CLI version and immutable source revision for every readiness result. Consumers can reject stale or mismatched readiness producers before they use host evidence. For more information, refer to System Readiness.
• Provider-neutral runtime bundles now enforce provider, workload, ownership, and registry contracts for the existing Docker and Kubernetes paths. Root-owned managed shared-state transactions enforce atomic application and rollback contracts but remain inactive in production onboarding. Neither foundation activates a new runtime provider or adds a CLI, configuration, default, or support claim.
• Documentation now includes a focused Deep Agents Code operation page, publishes the agentic-documentation guide in every guide variant, and uses host capability detection for optional NVIDIA DORI routing. It also adds missing recovery, memory-search, and two-DGX Station verification guidance identified by post-tag documentation audits. For more information, refer to Run LangChain Deep Agents Code and Engineer Documentation for AI Agents.
• Trusted E2E now binds request proofs to explicit authenticated phases, keeps calibration ancestry durable after evidence-source PR refs disappear, and validates coupled MCP credential evidence. Recovery repetition moved into deterministic integration tests, while the retained live test verifies one exact replacement process and connect-driven recovery. The PR Review Advisor now preserves validated second-opinion lane disagreements and rejects malformed E2E collections.

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 runtime identity, two-DGX Station vLLM, and memory search guides are now separate focused pages. The NVIDIA DORI installation pin is corrected 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.

NemoClaw v0.0.98 upgrades managed Hermes to 0.19.0 and adds structured non-interactive output for LangChain Deep Agents Code, no-clobber skill installation, and explicit storage-remediation readiness evidence. It also repairs post-reboot delivery recovery, OpenShell-preserving uninstall, messaging conflict enforcement, Docker host diagnostics, sandbox dependency baselines, and bounded runtime diagnostics.

NemoClaw v0.0.97 adds read-only host readiness reporting, a Deferred automatic two-Station vLLM evaluation, compatible-endpoint reasoning effort controls, and an experimental runtime identity reference for direct OpenClaw blueprints. It also hardens compatible-provider switching, managed sandbox images, Jetson GPU access, lifecycle recovery, network policy guidance, MCP discovery, and release E2E evidence.

NemoClaw v0.0.96 adds persistent baseline network policy exclusions, DNS-backed HTTPS inference switching, host-managed default OpenShell gateways, and opt-in MCP tool discovery. It also hardens blueprint identifier validation, improves onboarding and recovery diagnostics, preserves Shields posture during bulk backups, locks and updates managed sandbox image dependencies, reduces Hermes image size, and strengthens release validation.