Agent Switchboard

NVIDIA NeMo Agent Toolkit

by NVIDIA

VerifiedOfficial

Official listing: built and published by NVIDIA. More from 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.

Use it now

Keep it with up to 9 other tools you're setting up, then share them all as one link.

Try this first

Ask your assistant, with NVIDIA NeMo Agent Toolkit connected:

  • Run and Serve Workflows

    Use NVIDIA NeMo Agent Toolkit to run YAML-defined agent workflows: ‹what you need›

  • Workflow Evaluation

    Use NVIDIA NeMo Agent Toolkit to score the accuracy of agent workflows against datasets: ‹what you need›

  • Parameter and Prompt Optimizer

    Use NVIDIA NeMo Agent Toolkit to search hyperparameters: ‹what you're looking for›

Connect it over MCP

Ask your coding agent to set it up

Connect NVIDIA NeMo Agent Toolkit as an MCP server, following its setup instructions at https://docs.nvidia.com/nemo/agent-toolkit/latest/get-started/quick-start.html

Setup guide: docs.nvidia.com/nemo/agent-toolkit/latest/get-started/quick…

Install the CLI

pip
pip install nvidia-nat

Setup guide: docs.nvidia.com/nemo/agent-toolkit/latest/get-started/quick…

Call the API

Auth None needed

Setup guide: docs.nvidia.com/nemo/agent-toolkit/latest/get-started/quick…

Compare

Press Compare to add it to the tray at the bottom of the window, then pick up to 2 others anywhere on the site.

Access
APICLIMCP
Auth
None
Skills
4

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

Related Agents

fast-agent

CLI · API · MCP

Define and run multi-agent workflows in Python with first-class MCP support — chains, routers, parallel fan-out…

Verifiedby evalstate · Orchestration · 3 skills · API Key

Sage

API

Runs, evaluates and improves AI agents from task feedback, keeping each version with its evidence, via a desktop app, a…

VerifiedNewby ZHangZHengEric · Orchestration, Infrastructure & Ops · 5 skills · Bearer Token

VoltAgent

API · CLI

Builds TypeScript AI agents with tools, memory, and sub-agent supervision, paired with a local observability console…

Verifiedby VoltAgent · Orchestration, Code & DevTools · 3 skills · API Key

Cursor Agent SDK

API · CLI

Lets developers define, test, evaluate, and deploy agents as Markdown and TypeScript code, on Cursor-managed hosting or…

VerifiedOfficialNewby Anysphere · Orchestration, Code & DevTools · 5 skills · API Key
See 8 alternatives
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.
try this first
Ask your assistant, with NVIDIA NeMo Agent Toolkit connected:
Use NVIDIA NeMo Agent Toolkit to run YAML-defined agent workflows: ‹what you need›nat-run-serve
Use NVIDIA NeMo Agent Toolkit to score the accuracy of agent workflows against datasets: ‹what you need›nat-eval
Use NVIDIA NeMo Agent Toolkit to search hyperparameters: ‹what you're looking for›nat-optimize
use it now
Connect NVIDIA NeMo Agent Toolkit as an MCP server, following its setup instructions at https://docs.nvidia.com/nemo/agent-toolkit/latest/get-started/quick-start.htmlmcp.setup-prompt
https://docs.nvidia.com/nemo/agent-toolkit/latest/get-started/quick-start.htmlmcp.docs
pip install nvidia-natcli.install (pip)
https://docs.nvidia.com/nemo/agent-toolkit/latest/get-started/quick-start.htmlcli.docs
None neededapi.auth
https://docs.nvidia.com/nemo/agent-toolkit/latest/get-started/quick-start.htmlapi.docs
fields
nameNVIDIA NeMo Agent Toolkit
providerNVIDIA
urlhttps://github.com/NVIDIA/NeMo-Agent-Toolkit
categoriesorchestration
accessapi · cli · mcp
authnone
streamingtrue
pushfalse
verifiedtrue
officialtrue · NVIDIA
sponsoredfalse
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…
alternatives
/agents/nvidia-nemo-agent-toolkit/alternatives8 listedfast-agent, sage-agent-platform, voltagent
compare
/compare?a=nvidia-nemo-agent-toolkit&b=fast-agent&c=sage-agent-platformwith fast-agent, sage-agent-platform
→ https://github.com/NVIDIA/NeMo-Agent-Toolkit