Skip to navigation
Documentation

About Agents

View as Markdown

An agent on NeMo Helix is an agent entity in a workspace. Once registered, the platform can deploy it, route requests to it, collect its traces, evaluate it, and optimize it. Agents run through NeMo Fabric, which gives every supported harness (DeepAgents, Claude Code, Codex, Hermes, NOOA, or a remote agent endpoint) the same configuration, lifecycle, and telemetry.

How It Works

traces Client Agents gateway Agent deployment Inference Gateway Models Intake
  1. Register. nemo agents create stores the agent’s agent.yaml and uploads the files beside it to the agent’s <name>-ethos fileset.
  2. Deploy. nemo agents deploy runs the agent as a local subprocess, a Docker container, or a Kubernetes Deployment.
  3. Invoke. The Agents gateway routes each request to the agent’s active deployment and exposes it as an OpenAI-compatible endpoint, whatever the runtime.
  4. Call models. Model traffic from the agent goes through the Inference Gateway, which resolves model and virtual model names and attaches provider credentials. Agent configs never carry provider API keys for platform-routed models.
  5. Trace. Deployed agents export trajectories to Intake under the agent’s name by default, which feeds Insights, evaluation, and optimization.

Agent Lifecycle

StageCommand
Registernemo agents create --name <name> --agent-config <path>
Deploynemo agents deploy --agent <name>
Invokenemo agents invoke --agent <name> --input "..."
Chatnemo agents chat --agent-deployment <deployment>
Run once as a jobnemo agents execute --agent <name> --input "..."
Analyze tracesnemo insights analysis-runs create --agent <name>
Optimizenemo agents optimize run-strategy --strategy <strategy> --agent <name>
Update in placenemo agents redeploy --agent <name> --agent-config <path>
Tear downnemo agents undeploy --agent <name>, then nemo agents delete <name>

To try an agent.yaml without registering it, run nemo agents invoke --agent-config <path> --input "...".

Next Steps