nvidia-nat-core
Core library for NVIDIA NeMo Agent Toolkit
Decision gist · record as of 2026-08-14
Yes, if you are building or integrating agents into an existing system and need framework-agnostic composition, observability, and evaluation. The low install friction and active maintenance support the use case. No, if you are new to agent development—the documentation explicitly recommends installing from source for first-time users. The 31 runtime dependencies are substantial; evaluate whether the full stack fits your deployment constraints.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.11 or later (supports 3.11, 3.12, 3.13).
- Depends on FastAPI and uvicorn for server functionality.
- Low install friction with a pure-Python wheel.
License · maintenance · safety
Apache-2.0 (permissive) — Apache-2.0 permissive license allows commercial and private use without restriction, provided you retain copyright and license notices.
last release 2026-06-17 (58 days) · last repo commit 2026-08-12 · 2,576 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 256,809 downloads/mo, #8,456 on PyPI
Alternatives
Verify before relying
pip install nvidia-nat-core
from nvidia_nat_core import Agent
agent = Agent(name="my_agent")- Whether pre-built agents, tools, and workflows are included in this package or must be sourced separately
- Specific capabilities of the UI chat interface and whether it is bundled or requires separate installation
- Integration scope with Model Context Protocol (MCP) servers and whether MCP client is included
- Whether observability integrations (LangSmith, Phoenix, Arize AX, W&B Weave) are built-in or require additional setup
What it is and what it does
NVIDIA NeMo Agent Toolkit is a Python library that provides a composable foundation for building agents that work with any underlying agentic framework. It abstracts agents, tools, and workflows as reusable function calls, enabling developers to build once and deploy across different contexts without replatforming. The library includes profiling and observability hooks for monitoring token usage, latency, and bottlenecks across agent and tool boundaries, plus built-in evaluation tools for validating workflow accuracy.
The package depends on a substantial stack: FastAPI and Starlette for HTTP handling, Pydantic for validation, pymilvus for vector database integration, and cryptographic libraries for authentication (authlib, PyJWT, cryptography). It is designed for developers already familiar with agent-based systems who need to integrate NeMo Agent Toolkit into existing projects; the documentation recommends installing from source for first-time users.
Use it for
- Build a reusable agent that works across multiple frameworks without rewriting core logic
- Profile and debug agentic workflows to identify performance bottlenecks at the tool and agent level
- Integrate enterprise data sources and tools into agents via a unified function-call interface
- Monitor agent behavior and token usage with OpenTelemetry-compatible observability platforms
- Evaluate and validate the accuracy of multi-step agentic workflows before production deployment
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you are building or integrating agents into an existing system and need framework-agnostic composition, observability, and evaluation.
The low install friction and active maintenance support the use case. No, if you are new to agent development—the documentation explicitly recommends installing from source for first-time users. The 31 runtime dependencies are substantial; evaluate whether the full stack fits your deployment constraints.
Install
nvidia-nat-core on PyPI
Before you install
Low install friction with a pure-Python wheel. Active maintenance with recent releases; last commit 2026-08-12. Moderate dependency footprint (31 runtime packages including FastAPI, Pydantic, and vector database support via pymilvus) typical for a full-featured agent framework.
Requires Python 3.11 or later (supports 3.11, 3.12, 3.13). Depends on FastAPI and uvicorn for server functionality.
License in practice
Apache-2.0 permissive license allows commercial and private use without restriction, provided you retain copyright and license notices.
Quickstart
pip install nvidia-nat-core
from nvidia_nat_core import Agent
agent = Agent(name="my_agent")Verify before relying
- Whether pre-built agents, tools, and workflows are included in this package or must be sourced separately
- Specific capabilities of the UI chat interface and whether it is bundled or requires separate installation
- Integration scope with Model Context Protocol (MCP) servers and whether MCP client is included
- Whether observability integrations (LangSmith, Phoenix, Arize AX, W&B Weave) are built-in or require additional setup
Package facts
| License | Apache-2.0 permissive |
| Python support | Supports the current Python release <3.14,>=3.11 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 31 packagesaiofilesauthlibclickcoloramaexpandvarsfastapihttpxjinja2jsonpath-ngnest-asyncio2networkxnvidia-nat-atifnumpypandaspippkcepkginfoplatformdirspydanticpyjwtpymilvuspython-dotenvpython-multipartPyYAMLrichstarlettetabulatetzlocaluvicorncryptography |
| Maintenance | Actively maintained 58 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 256,809 / month, #8,456 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Programming Language :: PythonProgramming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13 |
Evidence: nvidia_nat_core-1.8.0-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “agentic workflow composition”
- nvidia-nat-coreNVIDIA NeMo Agent Toolkit is a framework-agnostic library for…
- nvidia-natIntegrates enterprise agents with data sources and tools across any…
- langchainLangChain provides a framework for building agents and LLM-powered…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also nvidia-nat · nvidia-nat-atif · nvidia-nat-opentelemetry · nemo-gym · nvidia-nat-mcp · nvidia-nat-eval · nvidia-nat-langchain · nemo-relay · nemoguardrails · agent_governance_toolkit