Release Notes

July 22, 2026

v0.0.92

NemoClaw v0.0.92 updates OpenClaw and its sandbox Node.js runtime, documents headless deployment, and strengthens security, installer, platform, and live E2E validation.

  • OpenClaw sandboxes now use OpenClaw 2026.7.1 and Node.js 22.23.1. The reviewed build remediates vulnerable Axios plugin copies and the affected OpenTelemetry Jaeger diagnostics graph with integrity-pinned packages. It also locks patched mcporter dependencies, preserves device-scope enforcement and private state during upgrades, and validates upgrades from NemoClaw v0.0.89. A real-artifact regression confirms malformed Jaeger trace and baggage headers do not terminate the diagnostics process.
  • Remote deployment guidance now uses one provider-neutral headless Linux server workflow for OpenClaw, Hermes, and Deep Agents Code. The guide covers unattended installation, loopback-only access, readiness checks, policy setup, updates, and recovery after a host reboot. Retired Brev deployment routes redirect to the shared workflow. For more information, refer to Deploy NemoClaw to a Headless Server.
  • Live E2E tests now report ordered semantic phases, outcomes, durations, resource-release timing, and secret-safe stall diagnostics. Each run saves a progress artifact that identifies where failures or stalls occurred. Collection-time validation rejects missing or invalid phase plans before tests use live infrastructure.
  • Installer integrity checks now accept the reviewed OpenShell Homebrew formula transition only when the template hash matches its exact release asset set. This maintains the fail-closed boundary while preserving the current archive-only installer contract.
  • Platform and image validation now compares canonical macOS watcher targets, raises the full WSL suite limit from 60 to 90 minutes, and capability-gates its Docker-only Hermes contract. The WSL tag test still verifies that a rejected concurrent update cannot replace latest. Hosted Hermes image exports now provision bounded swap before the final layer export. Hermes guard tests raise the child-process allowance from 5 to 90 seconds and use WSL fixtures that match production ownership. The validation and test changes do not alter runtime behavior or final image contents.
  • The canonical changelog now includes the previously missed v0.0.91 entry and corrects its legacy inference-selector guidance to match the tagged code. This restores release-history validation without changing the immutable v0.0.91 tag.

v0.0.91

NemoClaw v0.0.91 strengthens completed sandbox images, makes rebuild replacement safer, documents the Hermes API token lifecycle, expands qualified DGX Station guidance, and restores historical release validation.

  • Completed OpenClaw, Hermes, and Deep Agents Code images now replace affected node-tar installations with reviewed versions and scan the final filesystem before publication. Current and historical OpenClaw security-revision verifiers also validate exact dependency versions, resolved archives, integrity metadata, executable identity, and transactional state restoration in constrained containers. For more information, refer to the OpenClaw 2026.6.10 Dependency Review.
  • Rebuilds now carry validated local-base trust through Deep Agents Code image preparation, reuse the outer state backup during inner onboarding, and wait for OpenShell to confirm sandbox deletion before removing registry state or creating a replacement. These checks prevent rebuild from rejecting its own current base, taking a second backup against stale gateway state, or racing an asynchronous sandbox deletion. For more information, refer to Recover and Rebuild Sandboxes and the NemoClaw CLI Commands Reference.
  • Hermes guidance now explains when the API bearer token remains stable, when rebuild or invalid state rotates it, and how to retrieve the current value with nemohermes <sandbox> gateway-token --quiet instead of reading the generated environment file. For more information, refer to the NemoHermes CLI Commands Reference and Recover and Rebuild Sandboxes.
  • DGX Station documentation now records qualified single-system GB300 profiles as tested with limitations while keeping dual-Station and dedicated-CI gaps explicit. Coding-agent guidance also constructs non-interactive installs with explicit agent, provider, and release-tag variables and keeps Docker approval command-scoped. For more information, refer to Platform Support and Launch Claims, Prepare DGX Station to Install NemoClaw, and the NemoClaw Quickstart with OpenClaw.
  • Historical OpenClaw gateway-upgrade and Hermes rebuild fixtures now use immutable reviewed inputs that match each pinned release’s contract. This restores deterministic coverage for legacy image upgrades, Hermes token rotation, stale-base replacement, and completed-image security checks without weakening production validation.