> This page is for version Latest (default).
> For other versions, use one of these documentation indexes:
> - Latest (default): https://docs.nvidia.com/nemoclaw/latest/llms.txt

> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemoclaw/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemoclaw/_mcp/server.

## v0.0.67

NemoClaw v0.0.67 improves onboarding recovery, messaging reliability, OpenClaw agent workflows, and AI-agent documentation routing:

* Onboarding and OpenClaw agent operations recover more reliably after interrupted or scripted runs.
  NemoClaw keeps repair backstops active when `onboard --resume` continues from later nonterminal onboarding phases, and `agents apply` removes orphan OpenClaw agents without forwarding a delete flag that the OpenClaw CLI rejects.
  For more information, refer to [NemoClaw CLI Commands Reference](/user-guide/openclaw/reference/commands).
* Discord messaging now uses the managed proxy path that OpenClaw accepts.
  NemoClaw no longer writes a non-loopback per-account Discord proxy, while Telegram keeps its per-account proxy behavior, and WhatsApp policy E2E checks avoid brittle shell-pipeline failures on large policy output.
  For more information, refer to [Choose Messaging Channels](/user-guide/openclaw/manage-sandboxes/messaging-channels/choose-messaging-channels).
* AI-agent documentation now uses one compact routing skill instead of generated page-copy skills.
  The `nemoclaw-user-guide` skill points agents to the docs MCP server, `llms.txt`, and canonical Markdown routes so the docs site remains the source of truth.
  For more information, refer to [Use NemoClaw Docs with Your Coding Agents](/user-guide/openclaw/resources/agent-skills).