NVIDIA/NeMo-Agent-Toolkit v1.3.0

v1.3.0

Repository: NVIDIA/NeMo-Agent-Toolkit

Tag: v1.3.0

Published: 2025-10-24T21:26:58Z

Prerelease: no

Release notes:

What's Changed

🚀 Notable Features and Improvements

• ADK Support: Supports Google Agent Development Kit (ADK). Adds tool calling, core observability, and LLM integration in this release.
• Control-Flow Agents: Sequential Executor (Linear Agent) and Router Agent now control flow patterns of tool calls and sub-agents.
• Function Groups: Packages multiple related functions together so they share configuration, context, and resources.
• Hyperparameter Agent Optimizer: Automates hyperparameter tuning and prompt engineering for workflows.
• Introductory Notebook Improvements: Reorganizes getting started notebooks and adds Open in Colab links.
• LLM Improvements
• Adds LiteLLM Provider
• Supports GPT-5 (/chat/completions endpoint only)
• Adds Nemotron thinking configuration
• MCP Improvements
• Supports streamable-http - sse is no longer the default transport type.
• Supports initial authorization - Enables connecting to MCP servers that require authentication.
• Supports multiple MCP tools from a single configuration - Pulls in entire tool sets published by MCP servers or filters them based on user configuration.
• Enhances CLI utilities for MCP servers and clients - Improves the nat mcp sub command for querying, calling, and listing tools.
• Python 3.13 support

🚨 Breaking Changes

• Redis Configuration Changes in @willkill07 in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/649
• MCP enhancements: improves server config and adds support for all transport types (stdio, streamable-http) by @AnuradhaKaruppiah in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/718
• Move MCP client to a separate sub-package by @AnuradhaKaruppiah in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/768
• Signature change for BaseAgent by @yczhang-nv in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/757
• Builtin GitHub tools switched to Function Groups by @willkill07 in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/684
• Fix chat history support in tool_calling_agent by @gfreeman-nvidia in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/837
• Change nat mcp to a command group with serve and client subcommands by @zhongxuanwang-nv in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/811
• Builder get_* functions should be marked async by @willkill07 in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/834
• MCP Client Auth Support (part-2) by @AnuradhaKaruppiah in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/854
• ReWOO Agent Workflow Refactoring (Dependency DAG for async Executor). by @billxbf in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/861
• Reduce phoenix dependencies by @willkill07 in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/985
• Remove example with poor performance by @dagardner-nv in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/1011
• Deprecate the WeaveTelemetryExporter.entity field by @dagardner-nv in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/1016
• Syncing UI submodule to bring secure proxy server updates by @ericevans-nv in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/1044

✨ New Features

• Add features nat workflow create a versioned dependency and data and symlinks folder by @zhongxuanwang-nv in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/639
• Feature: Azure OpenAI LLM provider and client by @willkill07 in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/643
• Timezone Support for datetime Tool and Normalize Response Time Handling by @zhongxuanwang-nv in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/660
• Feature: GPT-5 Support by @willkill07 in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/664
• Customize Log Truncation in Config by @RohanAdwankar in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/723
• feat: Support for Nemotron thinking configuration by @willkill07 in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/717
• Track agent system prompt in config and add config to skip maintenance check by @hsin-c in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/724
• Add nvidia-nat-data-flywheel subpackage with NeMo Data Flywheel integrations by @mpenn in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/716
• Enhance ProcessingExporter system to support redaction of content in telemetry traces by @mpenn in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/751
• feat: Python 3.13 support by @willkill07 in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/761
• Add test LLM provider to support testing by @zhongxuanwang-nv in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/764
• Support additional provider parameters in LLM and Embedder config by @YosiElias in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/749
• Add return_direct option to tool_calling_agent for direct tool responses by @thepatrickchin in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/775
• Enable MCP auth for NAT MCP clients by @AnuradhaKaruppiah in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/752
• Add function group filtering by @willkill07 in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/807
• Implement Sequential Executor tool by @yczhang-nv in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/806
• Add a /debug route to NAT MCP frontend to expose MCP tools by @zhongxuanwang-nv in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/813
• MCP OAuth2 Token Introspection Validator by @ericevans-nv in...