NVIDIA/NeMo-Agent-Toolkit

Score: 74.1 Rank #11

The NVIDIA NeMo Agent toolkit is an open-source library for efficiently connecting and optimizing teams of AI agents.

Overview

NVIDIA/NeMo-Agent-Toolkit is a Python agent tool licensed under Apache-2.0. The NVIDIA NeMo Agent toolkit is an open-source library for efficiently connecting and optimizing teams of AI agents.

Ranked #11 out of 25632 indexed tools.

In the top 1% of all indexed tools.

Has 1,917 GitHub stars.

Used by 42 other projects.

Has 74 contributors.

Actively maintained with commits in the last week.

Ecosystem

Python Apache-2.0

Signal Breakdown

Stars 1,917

Freshness 2d ago

Issue Health 88%

Contributors 74

Dependents 42

Forks 553

Description Good

License Apache-2.0

How to Improve

Description low impact

Expand your description to 150+ characters for better discoverability

Badge

AgentRank score for NVIDIA/NeMo-Agent-Toolkit

Markdown

[![AgentRank](https://agentrank-ai.com/api/badge/tool/NVIDIA--NeMo-Agent-Toolkit)](https://agentrank-ai.com/tool/NVIDIA--NeMo-Agent-Toolkit)

HTML

<a href="https://agentrank-ai.com/tool/NVIDIA--NeMo-Agent-Toolkit"><img src="https://agentrank-ai.com/api/badge/tool/NVIDIA--NeMo-Agent-Toolkit" alt="AgentRank"></a>

Details

Stars: 1,917
Forks: 553
Open Issues: 41
Closed Issues: 299
Contributors: 74
Dependents: 42
Language: Python
License: Apache-2.0
Last Commit: 2d ago

Matched Queries

"agent tool"

From the README

# NVIDIA NeMo Agent Toolkit

<div align="center">

*NVIDIA NeMo Agent Toolkit adds intelligence to AI agents across any framework—enhancing speed, accuracy, and decision-making through enterprise-grade instrumentation, observability, and continuous learning.*

</div>

## 🔥 New Features

- [**Dynamo Runtime Intelligence:**](./examples/dynamo_integration/latency_sensitivity_demo/README.md) 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):**](https://docs.langchain.com/oss/python/integrations/providers/nvidia#install-2) 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.
- [**LangSmith Native Integration:**](./docs/source/run-workflows/observe/observe-workflow-with-langsmith.md

Read full README on GitHub →

View on GitHub →

Are you the maintainer? Claim this listing