Release Notes

August 23, 2026

v0.0.114

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.

  • Managed LangChain Deep Agents Code automation can invoke one uniquely registered, coherently read-only MCP tool with dcode tools call-read-only TOOL --json without model participation. The command accepts one bounded JSON object on standard input, rejects ambiguous or mutating tools, bounds execution and cleanup, redacts recognized credential-shaped output, and returns one versioned JSON envelope. For more information, refer to Run LangChain Deep Agents Code and the NemoClaw CLI Commands Reference. Related change: PR #9894.
  • nemoclaw <name> connect --probe-only, nemohermes <name> connect --probe-only, and nemo-deepagents <name> connect --probe-only now report credential-free elapsed time for each readiness stage. The timing line identifies lifecycle and forwarding actions and names the failed stage when available without changing the command’s readiness exit status. For more information, refer to Deploy NemoClaw to a Headless Server and the NemoClaw CLI Commands Reference. Related change: PR #9865.
  • Sandbox destruction now warns before terminating active SSH sessions, including unattended runs that use --yes or --force. OpenClaw session tar export now reports a retained in-sandbox staging artifact and its exact manual removal command when cleanup fails, because the artifact can contain pasted secrets. Host-mount diagnostics report the actual failed directory condition, and pending OpenClaw scope upgrades identify the exact device-review path. For more information, refer to the NemoClaw CLI Commands Reference and Understand Sandbox State. Related changes: PR #9782, PR #9787, PR #9853, and PR #9858.
  • Snapshot restore now preserves sealed OpenClaw configuration, and rebuild verifies final OpenClaw configuration integrity before it reports success. Shields timer authority retires only after lifecycle gates complete. For more information, refer to Create and Restore Snapshots and Recover and Rebuild Sandboxes. Related changes: PR #9231, PR #9791, and PR #9866.
  • Installation now fails closed when neither sha256sum nor shasum can verify the nvm installer before a required Node.js installation or upgrade. Hermes retries throttled source archive downloads. For more information, refer to Prerequisites and Troubleshooting. Related changes: PR #9776 and PR #9822.
  • Managed vLLM onboarding restores DGX Station large-model selection and strengthens fixed-profile selection, running-server reuse, and resumed-session validation. Portable Podman inference validation gives the first real completion request a 120-second deadline within a 150-second outer wait while retaining the existing readiness, GPU, identity, and cleanup bounds. Recovery now distinguishes bind refusals for Ollama, unauthenticated compatible endpoints, and backends whose type is unavailable. Protected loopback-route diagnostics also name the endpoint that the route fronts. For more information, refer to Use vLLM, Configure Inference Timeouts, and Troubleshooting. Related changes: PR #9836, PR #9843, PR #9852, PR #9868, and PR #9906.
  • Managed llama.cpp images include the required patched dependencies, bind lifecycle receipts to published software bill of materials files, and isolate platform-specific receipt pulls. For more information, refer to Choose a Local Inference Server. Related changes: PR #9821, PR #9849, and PR #9857.
  • Portable keeps its Podman proxy setting attached across process boundaries so later lifecycle work retains the selected proxy behavior. The inference model-limit documentation now shows each agent only the settings it supports and states that Deep Agents Code has no equivalent model-limit operation. For more information, refer to Configure Model Limits. Related changes: PR #9785 and PR #9867.
  • Ordinary Docker-driver onboarding for stock OpenClaw, Hermes, and LangChain Deep Agents Code now selects an immutable managed-image digest for the release and host architecture. If registry or catalog availability prevents selection, NemoClaw can build the shipped reviewed Dockerfile; invalid or inconsistent managed-image evidence stops before sandbox creation. Explicit --from Dockerfiles and Portable onboarding retain their separate paths. For more information, refer to the NemoClaw Quickstart with OpenClaw and Architecture Details. Related change: PR #9323.
  • Managed single-host vLLM onboarding can select the host GPU by index or full NVIDIA GPU UUID with --vllm-gpu-device. The selection is independent of sandbox GPU access, controls Docker placement and GPU preflight checks, and persists across resume. For more information, refer to Set Up vLLM and the NemoClaw CLI Commands Reference. Related change: PR #10025.
  • Static messaging credentials now use validated endpointless OpenShell provider profiles across onboarding and channel lifecycle operations. Paused detailed channel status keeps its schema-version-1 report envelope, skips the live probe, and returns an informational success. Channel start defers credential-bound policy activation until rebuild attaches the required provider; stopped Hermes Discord retains only its exact validated static provider without starting the channel or recreating credentials. For more information, refer to Manage Messaging Channels and the NemoClaw CLI Commands Reference. Related changes: PR #9913, PR #10021, PR #10026, PR #10047, and PR #10052.
  • Deep Agents Code progressive disclosure now derives loaded MCP tools from the pinned executable catalog and rejects duplicate loaded implementations. Tools discovered after startup become searchable only after the runtime loads them. For more information, refer to Configure Progressive Tool Disclosure. Related change: PR #10031.
  • Portable lifecycle recovery now reports one credential-free timing line with fixed stage durations, selected actions, attempt counts, result, and failed stage. OpenClaw onboarding produces a missing canonical local CLI write-scope request before final observation, while Portable settlement recognizes the same exact request when it is already pending and avoids creating a duplicate. Both paths approve at most once and require strict same-device settled state before completion. For more information, refer to the NemoClaw CLI Commands Reference. Related changes: PR #9964, PR #10018, and PR #10022.
  • The maintained nemoclaw update installer request and every redirect now require HTTPS. For more information, refer to the NemoClaw CLI Commands Reference. Related change: PR #9862.
  • Legacy GPU sandbox recovery now corroborates final replacement handoff with the transaction-owned full container ID instead of stale sandbox-name metadata. This prevents a healthy replacement from waiting through the full handoff deadline when legacy metadata differs. For more information, refer to Recover and Rebuild Sandboxes. Related change: PR #10053.