Release Notes

July 31, 2026

v0.0.100

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. 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. 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.