NeMo Helix

Make the agents you ship faster, more accurate, and safer.

NeMo Helix is an open source control plane for improving and hardening production agents. It runs on your infrastructure and plugs into your platform. Evaluate behavior, test changes and measure the results through repeatable workflows. Run Helix locally or on Kubernetes, and access it through REST APIs, a CLI or a Python SDK. Helix also includes NeMo Studio, a lightweight web UI for observability and orchestration.

NeMo Helix uses modular plugins for the infrastructure agents need to run at scale. Choose the capabilities you need, from agent execution and sandboxing to file storage, secrets, authentication, model management and inference middleware. Each comes with a default implementation that you can replace with your own infrastructure or tools.

What You Can Do

• Secure agents. Guardrails (content safety, jailbreak detection, PII redaction), garak (red-teaming via garak), Anonymizer (PII handling for training data).
• Evaluate agents. LLM-as-judge, deterministic, agentic, and RAG benchmarks. Harbor-backed eval suites for regression testing.
• Tune agents. Skill optimization, prompt and hyperparameter tuning, Switchyard model routing.
• Build agents. Create platform-managed agents with agent.yaml, with legacy support for NAT-based LangGraph agents. Shared infrastructure: Inference Gateway, Secrets, Files, Entity Store, Jobs.
• Run agents. Deploy and manage agents interactively or as long-running jobs.
• Generate synthetic data. Generate synthetic data for training or evaluation purposes using Data Designer.
• NeMo Studio (alpha). Installed automatically with the platform. Studio is a browser UI for chatting with agents and models, starting and monitoring various jobs, and reviewing results. Studio’s agent-focused features are still a work in progress; the CLI is the primary surface today.

Platform Capabilities

The platform provides several shared capabilities to NeMo libraries.

• Models and Inference for model providers, virtual models, and gateway calls.
• Files, Secrets, Entities, and jobs for storing state and running local work.

Architecture Diagram

Where to Go Next

• Setup - install, configure providers, and run local services.
• About Agents - learn the managed agent lifecycle.
• Optimize Agents - improve cost, quality, and model routing.
• Add Guardrails to an Agent - route agent model traffic through input and output rails.
• Scan Trace Data - check agent traces for PII and leaked credentials.