| title |
|
||||||||
|---|---|---|---|---|---|---|---|---|---|
| description |
|
||||||||
| keywords |
|
||||||||
| topics |
|
||||||||
| tags |
|
||||||||
| content |
|
||||||||
| status | published |
NVIDIA NemoClaw is available in early preview starting March 16, 2026. Use this page to track changes.
NemoClaw v0.0.40 improves onboarding reliability, local inference setup, and sandbox recovery:
nemoclaw onboarduses the Docker-driver OpenShell gateway path on macOS with OpenShell 0.0.37, repairs incomplete Docker-driver installs before startup, and installs the platform-specific gateway asset it needs.- The Docker-driver gateway startup check waits for the gateway port to accept TCP connections before it reports the gateway as healthy, and startup failures now include child process exit details.
- Local Ollama setup requires the authenticated reverse proxy token on every native Ollama API route, including
GET /api/tags. - The Linux Ollama install path preflights
zstdbefore running the official installer and explains why each sudo-backed setup step needs elevated privileges. - The onboarding provider menu offers an already-running local vLLM server directly when
localhost:8000responds, while managed vLLM install and start options remain behind the experimental opt-in. - Policy tier defaults are filtered by active agent support, so presets such as Brave Search are not reapplied to agents that do not support that integration.
nemoclaw <name> connectchecks dashboard forward reachability with a TCP probe before it reports a forward as stale.- Sandbox startup captures a known-good OpenClaw config baseline and restores it on restart if
/sandbox/.openclaw/openclaw.jsonbecomes empty. - The NemoClaw OpenClaw plugin package declares compatibility metadata for OpenClaw package tooling.
NemoClaw v0.0.39 improves several day-two workflows:
- The installer checks Docker earlier on Linux, can install and start Docker when needed, and stops with
newgrp dockerguidance when the current shell has not picked up thedockergroup yet. - DGX Spark and DGX Station users can accept an express install prompt that preselects the local inference path and suggested policy defaults.
- NemoClaw now creates GPU-capable OpenShell Docker sandboxes by default when an NVIDIA GPU is available, with explicit
--sandbox-gpu,--no-sandbox-gpu, and--sandbox-gpu-devicecontrols. nemohermessupports Hermes Provider onboarding and runtime model switches throughnemohermes inference set.nemoclaw <name> hosts-add,hosts-list, andhosts-removemanage sandbox host aliases for LAN-only services.nemoclaw updatechecks and runs the maintained installer flow, whilenemoclaw upgrade-sandboxesremains responsible for rebuilding existing sandboxes.nemoclaw <name> destroypreserves the shared gateway by default unless--cleanup-gatewayis selected.nemoclaw <name> connectrepairs staleinference.localDNS proxy routes before opening the session.- Windows-host Ollama onboarding relaunches the daemon with the reachable binding after install or restart.
- Local NVIDIA NIM onboarding passes
NGC_API_KEYorNVIDIA_API_KEYinto the managed container without putting the secret in process arguments, detects early container exits during health checks, and prints a per-GPU preflight breakdown on mixed-model hosts. - The sandbox startup path strips additional Linux capabilities before and during privilege step-down.
- OpenClaw workspace template files are seeded when bootstrap is skipped and the workspace is still empty.
- Kimi K2.6 and related NVIDIA-hosted chat-completions paths include model-specific compatibility handling for reasoning output.
NemoClaw v0.0.38 improves several day-two workflows:
nemoclaw <name> statusshows the gateway's active policy version in the displayed policy YAML when OpenShell reports one.nemoclaw uninstallstops matching Local Ollama auth proxy processes before it removes~/.nemoclaw, which prevents stale listeners from blocking a later reinstall.- Local Ollama onboarding validates structured chat-completions tool calls and rejects models that leak tool-call payloads as plain text.
- Blueprint policy additions under
components.policy.additionsare validated, merged into the live policy, applied through OpenShell, and recorded in run metadata. - Rebuild backups tolerate partial archive output when usable data was produced, then report only the manifest-defined paths that could not be archived.
- NemoHermes uninstall output uses NemoHermes-specific help, progress, and completion text.
Starting with NemoClaw v0.0.34, the curl -fsSL https://www.nvidia.com/nemoclaw.sh | bash installer pipeline no longer auto-accepts the third-party software notice when stdin is piped and /dev/tty is unavailable (for example, deeply detached SSH sessions or some container shells).
In environments without a TTY, accept upfront in the pipe:
$ curl -fsSL https://www.nvidia.com/nemoclaw.sh | NEMOCLAW_ACCEPT_THIRD_PARTY_SOFTWARE=1 bashOr pass the flag through to the installer:
$ curl -fsSL https://www.nvidia.com/nemoclaw.sh | bash -s -- --yes-i-accept-third-party-softwareOr re-run from a terminal with a controlling TTY:
$ bash <(curl -fsSL https://www.nvidia.com/nemoclaw.sh)The installer error message in v0.0.35+ surfaces all three invocations directly so users can copy-paste a recovery without leaving the terminal.
NemoClaw pins the OpenClaw version inside the sandbox at build time via min_openclaw_version in nemoclaw-blueprint/blueprint.yaml; existing sandboxes do not auto-upgrade.
Run nemoclaw <name> status to see the OpenClaw version currently running in a sandbox, and nemoclaw <name> rebuild to pick up a newer pin from a NemoClaw upgrade.
See Checking the OpenClaw version for the full policy.