nvidia-nat

library1.8.0pypypiunverified

NVIDIA NeMo Agent Toolkit (nvidia-nat) is a Python library for building, training, and deploying conversational AI agents, including large language model (LLM) agents with tool use, memory, and multi-turn dialogue. Version 1.6.0 requires Python <3.14, >=3.11. Releases occur approximately monthly.

ai-ml llm-agents

pip install nvidia-nat

github ↗package ↗docs ↗

INSTALL

IMPORT

SIG · NVIDIA-NAT

nvidia-nat

ai-mlpythonv1.8.0

Install

18.6s avg

Import

—

Disk

307MB

Pass rate

6/ 10

Env Coverage6 / 10

glibc

3.9–3.13

musl

3.9–3.13

Install & Compatibility

Where this runs

tested against v1.8.0 · pip install

no network on importno background threads

Install × environment matrix

Each cell = how many times install + import succeeded across repeated harness runs. Partial = flaky.
glibc = Debian/Ubuntu slim · musl = Alpine Linux

musl

glibc

py 3.10

✕ build_error

py 3.11

✓ —

✓ 19.95s

py 3.12

✓ —

✓ 17.85s

py 3.13

✓ —

✓ 17.85s

py 3.9

✕ build_error

307MB installed

● package 307MB

Code

Verified usage

Verified import paths — ran on the pinned version, not inferred.

NemoAgent

✓ from nvidia_nat import NemoAgent

Primary class for creating an agent.

AgentConfig

✓ from nvidia_nat.config import AgentConfig

Configuration class for agent settings.

Initialize a NemoAgent with an API key from environment variable and send a chat message.

import os from nvidia_nat import NemoAgent from nvidia_nat.config import AgentConfig api_key = os.environ.get('NEMO_API_KEY', '') config = AgentConfig(api_key=api_key) agent = NemoAgent(config) response = agent.chat("Hello, how are you?") print(response)

Debug

Known issues

breakingIn version 1.6.0, the AgentConfig class is no longer defined in nvidia_nat directly; it must be imported from nvidia_nat.config. Old imports (from nvidia_nat import AgentConfig) raise ImportError.

fix

Update imports to 'from nvidia_nat.config import AgentConfig'.

affects: <=1.5.x

deprecatedThe method 'agent.call()' is deprecated in 1.6.0 and will be removed in 2.0. Use 'agent.chat()' instead.

fix

Replace agent.call() with agent.chat().

affects: >=1.6.0

gotchaCUDA is required for GPU acceleration. If torch is installed without CUDA, the library silently falls back to CPU, which is extremely slow for large models.

fix

Install PyTorch with CUDA: pip install torch --index-url https://download.pytorch.org/whl/cu118

affects: all

Upgrade

Version history

1.8.0latest on PyPI · released Jun 17, 2026

Audit

Dependencies

torchrequiredRequired for model inference and training; must be installed separately with CUDA support

transformersoptionalUsed for Hugging Face model integration; optional if using only local Nemo models

Agent activity

13 hits · last 30 days

node

OpenAI (training)

Resources

githubhttps://github.com/NVIDIA/NeMo-Agent-Toolkit ↗

packagehttps://pypi.org/project/nvidia-nat/ ↗

docshttps://docs.nvidia.com/nemo/agent-toolkit/latest/ ↗