NemoClaw Community
Explore reusable recipes, field demos, and developer tools—then narrow the catalog by type, provenance, collection, or industry.
Explore the catalog
Category combines artifact type with recipe provenance. Industry describes the workflow that the example serves.
Search the catalog
Search titles, descriptions, requirements, contributors, types, provenance, collections, and industries.
20 examples shown
Try a broader search, choose another view, or reset the filters above.
Reusable agent workflows authored or maintained by NVIDIA, designed as practical starting points that developers can inspect, adapt, and deploy with NemoClaw.
NVIDIA recipe
Helps learners work through the seven-module Build an Agent workshop in JupyterLab with an AI tutor that explains concepts, offers graduated hints, and checks progress inside an OpenShell sandbox.
NVIDIA recipe
Helps developer community leaders align priorities with demand by turning available GitHub, GitLab, forum, Slack, email, and web signals into evidence-grounded briefs, gaps, and follow-up recommendations.
NVIDIA recipe
Helps Kubernetes operators match GPU inference capacity to demand by pairing a CPU-only OpenShell sandbox with Ollama replicas that scale on utilization or latency and return to one after load.
NVIDIA recipe
Builds a revisable local memory from email and Slack, then ranks obligations against the user's priorities while preserving pins and ignores without changing source systems.
NVIDIA recipe
Helps developers choose and troubleshoot NVIDIA technologies by searching allowlisted documentation, repositories, model catalogs, and forums for current, evidence-linked answers.
NVIDIA recipe
Helps payment operators screen synthetic outbound payments, explain holds, and prepare review packets while OpenShell keeps final release authority with a human outside the Hermes sandbox.
NVIDIA recipe
Helps maintainers review exact pull request heads through staged, repository-aware Hermes analysis, producing attested JSON and Markdown findings for inspection before optional publication.
NVIDIA recipe
Helps quality engineers turn public GitHub pull request descriptions and bounded diffs into Slack briefs and proposed, unexecuted feature test cases with source evidence.
NVIDIA recipe
A team of Hermes bots you talk to from Hermes Desktop, one NemoClaw sandbox each. A bot reaches only what its policy names, and when it needs something it cannot reach, it asks a teammate.
NVIDIA recipe
Helps video analysts and engineers deploy and operate NVIDIA VSS profiles by chat, using a sandboxed agent that runs the Compose deployment through a host-side MCP server and reports the result.
Reusable NemoClaw agent workflows contributed by partner organizations, with attribution and implementation guidance preserved from each contributor.
Partner recipe · BlueTier Operations
Demonstrates a maker-checker gate for x402 payments: a sandboxed agent submits intents, while a host-side Blackwall verdict controls mock signing and settlement before any signature exists.
Partner recipe · HPE
Helps store employees check inventory and sales or request transfers and reorders through role-aware Telegram conversations scoped to their assigned store.
Partner recipe · Shrike Security, Inc.
Adds defense-in-depth action governance through an in-sandbox hook that checks each OpenClaw tool call against server-side Shrike policy and blocks prohibited or approval-required calls.
Partner recipe · Tavily
Tracks what changed across chosen web topics and why it matters, producing scheduled, deduplicated Markdown digests and JSON changelogs with source citations.
Reusable NemoClaw agent workflows contributed independently by community members, offering practical starting points for adaptation and experimentation.
Community recipe
Helps web teams find WCAG issues through a dedicated sandbox and host-side real Chrome, returning rule-level findings with optional screenshots, PDFs, recordings, and network traces.
Community recipe
Adds asynchronous research to a sandbox, so users can queue long-running jobs on a host-side worker, monitor persistent task state, and return later for text or JSON results.
Bounded NemoClaw demonstrations built for specific NVIDIA field scenarios, hardware, or software environments rather than general-purpose deployment.
NVIDIA field demo
Guides DGX Spark users through serving local multimodal models with llama.cpp, connecting an agent harness, and trying coding, vision, browser, messaging, and speech workflows.
NVIDIA field demo
Lets users direct a specialized Hermes agent on DGX Station across Blender and NVIDIA Omniverse workflows, producing scene edits, OVRTX renders, native OVPhysX simulations, and replay evidence.
Standalone utilities that help developers build, evaluate, inspect, or operate NemoClaw agents without defining an end-user agent workflow.
Developer tool
Measures memory built from synthetic email and chat, asks 186 questions on one corpus and 96 on a second, and reports accuracy by question type with ingest and answer token costs.
Developer tool
Provides an experimental loop for tuning DeepAgents harness profiles against behavioral evaluations, keeping fixes that pass verification and rolling back rejected edits.