NeMo-Agent-Toolkit

Supports Mcp

• AI Coding Agent Skills: Use focused NeMo Agent Toolkit skills to give coding agents task-specific guidance for building, evaluating, optimizing, and observing workflows.
• Dynamo Runtime Intelligence: Automatically infer per-request latency sensitivity from agent profiles and apply runtime hints for cache control, load-aware routing, and priority-aware serving.
• Agent Performance Primitives (APP): Introduce framework-agnostic performance primitives that accelerate graph-based agent frameworks such as LangChain, CrewAI, and Agno with parallel execution, speculative branching, and node-level priority routing.
• Public Plugin API for Third-Party Tools: Build provider-managed integrations against the public NeMo Agent Toolkit plugin API instead of framework-specific internal packages. Thank you to the maintainers of externally managed plugins including NeMo-Agent-Toolkit-Tavily, NeMo-Agent-Toolkit-Redis, and NeMo-Agent-Toolkit-ATR. This new workflow is intended to help third-party package maintainers bring their integrations into NeMo Agent Toolkit workflows more quickly. Note that these third-party packages are managed outside the NeMo Agent Toolkit repository and may release, change, or run CI on schedules independent of NeMo Agent Toolkit.
• LangSmith Native Integration: Observe end-to-end agent execution with native LangSmith tracing, run evaluation experiments, compare outcomes, and manage prompt versions across development and production workflows.
• FastMCP Workflow Publishing: Publish NeMo Agent Toolkit workflows as MCP servers using the FastMCP server runtime to simplify MCP-native deployment and integration.
• Migration notice: 1.5.0 simplifies package installation and dependency management. See the Migration Guide.

Before getting started, it's possible to run this simple workflow and many other examples in Google Colab with no setup. Click here to open the introduction notebook: .

1. Ensure you have set the NVIDIA_API_KEY environment variable to allow the example to use NVIDIA NIMs. An API key can be obtained by visiting build.nvidia.com and creating an account.

   export NVIDIA_API_KEY=<your_api_key>
   

2. Create the NeMo Agent Toolkit workflow configuration file. This file will define the agents, tools, and workflows that will be used in the example. Save the following as workflow.yml:

   functions:
      # Add a tool to search wikipedia
      wikipedia_search:
         _type: wiki_search
         max_results: 2
   
   llms:
      # Tell NeMo Agent Toolkit which LLM to use for the agent
      nim_llm:
         _type: nim
         model_name: nvidia/nemotron-3-nano-30b-a3b
         temperature: 0.0
         chat_template_kwargs:
            enable_thinking: false
   
   workflow:
      # Use an agent that 'reasons' and 'acts'
      _type: react_agent
      # Give it access to our wikipedia search tool
      tool_names: [wikipedia_search]
      # Tell it which LLM to use
      llm_name: nim_llm
      # Make it verbose
      verbose: true
      # Retry up to 3 times
      parse_agent_response_max_retries: 3
   

3. Run the Hello World example using the nat CLI and the workflow.yml file.

   nat run --config_file workflow.yml --input "List five subspecies of Aardvarks"
   

This will run the workflow and output the results to the console.

Workflow Result:
['Here are five subspecies of Aardvarks:\n\n1. Orycteropus afer afer (Southern aardvark)\n2. O. a. adametzi  Grote, 1921 (Western aardvark)\n3. O. a. aethiopicus  Sundevall, 1843\n4. O. a. angolensis  Zukowsky & Haltenorth, 1957\n5. O. a. erikssoni  Lönnberg, 1906']