switchboard
N

NVIDIA NeMo Agent Toolkit

by NVIDIA

Connects, profiles, evaluates, and optimizes agent workflows across frameworks like LangChain, LlamaIndex, and CrewAI, with MCP and A2A support and a `nat` CLI for Python developers.

4
Skills
None
Auth
Yes
Streaming
No
Push

Skills

Run and Serve Workflows

Runs YAML-defined agent workflows with `nat run` or serves them over a FastAPI server with streaming endpoints via `nat serve`.

Workflow Evaluation

Scores the accuracy of agent workflows against datasets with `nat eval` and records performance characteristics per run.

Parameter and Prompt Optimizer

Searches hyperparameters with Optuna and evolves prompts with a genetic algorithm via `nat optimize` to hit chosen metrics.

MCP Client and Server

Consumes remote MCP tools inside workflows and publishes workflow functions as MCP tools with the `nat mcp serve` command.

Orchestrationnvidiaagent-frameworkframework-agnosticagent-evaluationprofilingobservabilitya2aopen-source
Visit Agent
nvidia-nemo-agent-toolkit
Connects, profiles, evaluates, and optimizes agent workflows across frameworks like LangChain, LlamaIndex, and CrewAI, with MCP and A2A support and a `nat` CLI for Python developers.
fields
nameNVIDIA NeMo Agent Toolkit
providerNVIDIA
urlhttps://github.com/NVIDIA/NeMo-Agent-Toolkit
categoriesorchestration
accessapi · cli · mcp
authnone
streamingtrue
pushfalse
verifiedtrue
tagsnvidia, agent-framework, framework-agnostic, agent-evaluation, profiling, observability, a2a, open-source
skills
nat-run-serveRun and Serve WorkflowsRuns YAML-defined agent workflows with `nat run` or ser…
nat-evalWorkflow EvaluationScores the accuracy of agent workflows against datasets…
nat-optimizeParameter and Prompt OptimizerSearches hyperparameters with Optuna and evolves prompt…
nat-mcpMCP Client and ServerConsumes remote MCP tools inside workflows and publishe…