Release Notes

July 24, 2026

v0.0.95

NemoClaw v0.0.95 adds explicit ownership for externally supervised OpenShell gateways, strengthens recovery and state-transfer paths, expands inference compatibility, refreshes sandbox security packages, and requires E2E evidence from executed runs while separating runner wait time from test execution.

  • Platforms can now declare whether NemoClaw or an external systemd service owns the OpenShell gateway lifecycle. NemoClaw validates the declared listener and keeps stop, recovery, and uninstall operations from changing an externally supervised gateway. Stopping a sandbox now removes its dashboard forward, forward startup retries terminated listener attempts, and managed recovery retries dropped OpenShell relay connections. Hermes preserves managed gateway restart recovery. Uninstall keeps OpenShell-orphaned sibling sandboxes outside the selected cleanup scope. For more information, refer to Declare the OpenShell Gateway Lifecycle Authority, Run Sandboxes, Recover and Rebuild Sandboxes, and Uninstall NemoClaw.
  • Snapshot restore now replaces SQLite state files through staged atomic operations. Strict backup-all skips stranded orphan sandboxes, and nemoclaw <name> download verifies that each requested host artifact exists before reporting success. For more information, refer to Create and Restore Snapshots and the NemoClaw CLI Commands Reference.
  • Onboarding now reuses a reachable Ollama service on Windows hosts and falls back to the standard CDI directories when Docker reports no CDI specification directories. OpenRouter forwarding applies a connection-establishment deadline, and managed NVIDIA Build Nemotron-3 requests omit the unsupported top-level thinking field. Managed Deep Agents Code preserves configured headless retry limits while classifying provider failures. For more information, refer to Set Up Ollama, Configure Inference Timeouts, and NemoClaw Quickstart with Deep Agents.
  • When a base-image override is supplied, NemoClaw accepts only an official immutable remote digest or a local image built and pinned during the current operation. Rebuilds can reuse those local images, OpenClaw runtime checks validate version output, and shields preserve openclaw.json when a legacy lock has no config hash. The base images also update bundled npm packages, Perl, libexpat, and jq to address reviewed security findings, while the final OpenClaw image uses fewer payload layers. For more information, refer to Recover and Rebuild Sandboxes, Architecture Details, and the NemoClaw CLI Commands Reference.
  • The default OpenClaw Discord policy now allows the bot to manage its own application commands without granting unrelated Discord API access. For more information, refer to Choose Messaging Channels and Network Policies.
  • Release E2E automation no longer accepts a skipped PR gate as passing evidence. Root image changes select the full suite, direct main runs provision Hermes swap, retry reservations clean up after terminal outcomes, and runtime reports separate runner wait time from execution time. Nightly history and selected-test risk signals make infrastructure delays and product failures easier to distinguish.

v0.0.94

NemoClaw v0.0.94 strengthens sandbox restore and update behavior, adds machine-readable onboarding progress, improves policy and security evidence, reduces Hermes image build time, and makes live E2E failures easier to classify.

  • Snapshot restore now clears stale contents only from state directories declared by the snapshot manifest. It preserves target-only directories and directories whose backup failed. Cross-sandbox OpenClaw restores re-establish gateway pairing and verify it with an authenticated agent run. Hermes images repair virtual-environment access for the sandbox user, and session exports verify that each download produced the expected host artifact. For more information, refer to Create and Restore Snapshots and the NemoClaw CLI Commands Reference.
  • nemoclaw upgrade-sandboxes --check now reads sandbox state without starting, recovering, or selecting a gateway. When registered sandboxes resolve to one recorded gateway, the command queries that gateway instead of the gateway selected by the current environment. For more information, refer to Update Sandboxes.
  • policy-add now compares an already-applied catalog preset with the live policy. It exits without mutation when the content matches and previews the update when the preset changed. Network policy guidance now explains when an endpoint requires tls: skip raw TLS passthrough and identifies the lost L7 inspection and credential-resolution controls. For more information, refer to Apply Policy Presets, Configure Raw TLS Passthrough, Common NemoClaw Integration Policy Examples, and the NemoClaw CLI Commands Reference.
  • Onboarding now supports --events=jsonl for a versioned, redacted stream of canonical state-machine events. The human-readable progress stream remains on standard error, and closing or slowing the event stream does not cancel onboarding. DGX Spark resume preserves the selected managed vLLM Express path, managed vLLM rejects a model that does not support the detected platform before downloads, and compatibility recovery selects and probes one usable IPv4 resolver. For more information, refer to the NemoClaw CLI Commands Reference, Set Up vLLM, and Troubleshooting.
  • DGX Station qualification now accepts an OTA-upgraded GB300 release marker that omits DGX_OTA_PRETTY_NAME when the base workstation identity is present. The metadata override guidance now distinguishes recognized GB300 hardware from release-marker variants without weakening runtime checks. For more information, refer to Prepare DGX Station to Install NemoClaw.
  • sandbox doctor --json now redacts token-shaped values at both machine-readable output boundaries while preserving the exit status from the original report. Reviewed npm audits now retain scanner, registry, timing, package, advisory, report-path, and failure provenance. A read-only advisory correlation tool can identify exact npm package and range matches before a reviewed audit record appears, while ambiguous matches remain informational and do not block a release.
  • Hermes image assembly now groups repository payloads into five ownership-preserving BuildKit layers. The first hosted comparison reduced the production build step from 205 seconds to 101 seconds and the layer export from 178.8 seconds to 70.4 seconds. Build-time checks preserve file contents, modes, owners, scanner ordering, and cache boundaries.
  • Live E2E validation now isolates long-running lanes, trusts exact-head Hermes swap setup, stabilizes cancelled child lifecycles, parallelizes plugin EXDEV coverage, and records periodic runner-pressure telemetry. These changes distinguish hosted-runner loss from product failures while retaining the cold-onboard performance budget as a separate release signal. Documentation validation also keeps agent-variant checks read-only, accepts an absent Fern preview as a non-blocking condition, and uses Fern 5.80.1.