NVIDIA/NeMo-Agent-Toolkit v1.7.0

v1.7.0

Repository: NVIDIA/NeMo-Agent-Toolkit

Tag: v1.7.0

Published: 2026-05-21T18:15:22Z

Prerelease: no

Release notes:

🚀 Notable Features and Improvements

• Add AI coding agent skills for NeMo Agent Toolkit
• Add consent-gated runtime telemetry for NeMo Agent Toolkit CLI commands

What's Changed

🚨 Breaking Changes

• chore: migrate openai dependency from 1.x to 2.x by @willkill07 in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/1849
• chore: dependency cleanup - drops optuna chain and openinference from core by @bbednarski9 in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/1902
• Remove the nvidia-nat-vanna integration package by @dagardner-nv in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/1926

✨ New Features

• Add ATIF trajectory exporter for Phoenix visualization and debugging by @yczhang-nv in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/1869
• Add Exa Search API support as internet search tool by @maxwbuckley in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/1846
• Add OCI LangChain support for hosted Nemotron workflows by @fede-kamel in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/1804
• ATOF v0.1: Agentic Trajectory Observability Format (aligned spec) by @bbednarski9 in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/1890
• feat(cli): add consent-gated runtime telemetry for NAT CLI commands by @yczhang-nv in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/1897
• feat(observability): Arize AX OTLP exporter, docs, and examples by @ryoung562 in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/1898
• Feature: token streaming support for ReAct Agent by @thepatrickchin in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/1851

🔧 Improvements

• Misc CI improvements by @dagardner-nv in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/1866
• Misc CI improvements by @dagardner-nv in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/1867
• Support client-id-only MCP OAuth2 and refine Outlook auth example config by @AnuradhaKaruppiah in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/1885
• Misc test improvements and update model in the workflow template by @dagardner-nv in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/1884
• Widen the version range for starlette by @dagardner-nv in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/1887
• Filter AIMessage state updates from streaming output by @MylesShannon in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/1863
• Add optional --client-id and --client-secret flags to nat mcp client sub-commands by @dagardner-nv in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/1891
• dependency fix: remove flask as a hard dependency of nat-core by @bbednarski9 in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/1895
• dependency cleanup: move aioboto3, plotly, and wikipedia to dependent subpackages by @bbednarski9 in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/1896
• fix(tool): stop leaking exception details in chat_completion error response by @ColinM-sys in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/1876
• fix(example): Improve ADK-demo example with dynamic weather and time tools by @yczhang-nv in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/1927
• chore: bump dependency versions by @willkill07 in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/1931
• chore: bump dependency versions by @dagardner-nv in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/1936
• chore: Replace llama-3.2-nv-embedqa-1b-v2 with llama-nemotron-embed-1b-v2 by @dagardner-nv in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/1937
• chore: set dependency version range for azure-identity by @dagardner-nv in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/1942
• Replace llama-3.2-nv-rerankqa-1b-v2 with llama-nemotron-rerank-1b-v2 by @dagardner-nv in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/1944
• Update older models by @dagardner-nv in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/1960
• Adopt latest changes from NAT-UI by @dagardner-nv in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/1963
• Update model_health_check.py to check for deprecation header by @dagardner-nv in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/1974

🐛 Bug Fixes

• fix(memmachein): preserve conversation message order in add_items by @fede-kamel in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/1856
• Add an expiration time to cached MCP auth credentials by @dagardner-nv in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/1872
• Fix observability_evaluation_and_profiling example notebook by @dagardner-nv in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/1874
• Fix shutdown on Cntrl+c for ci/scripts/run_tests.py by @dagardner-nv in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/1886
• fix: preserve tool_calls in _stream_llm for native tool calling by @getglad in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/1864
• fix(mcp-client): set proper httpx timeouts for streamable-http transport by @yczhang-nv in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/1889
• fix(front-end): Fix HTTPInteractiveRunner streaming cleanup on client disconnect by @yczhang-nv in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/1916
• fix(deps): update selected dependency floors by @mnajafian-nv in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/1923
• fix(haystack): update urllib3 dependency floor by @mnajafian-nv in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/1922
• fix(agno): update Agno dependency stack by @mnajafian-nv in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/1919
• fix(fastmcp): update FastMCP to 3.2.4 by @mnajafian-nv in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/1918
• Remove currency A2A example from release validation by @AnuradhaKaruppiah in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/1924
• Update RL OpenPipe example by @dnandakumar-nv in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/1925
• fix(Phoenix): Fix Phoenix telemetry API key support by @yczhang-nv in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/1928
• fix(example): Fix typing.Any runtime checks in function conversion by @yczhang-nv in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/1949
• Fix MCP schema model reuse for Kaggle tools by @AnuradhaKaruppiah in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/1954
• fix(example): Fix auto-memory wrapper user ID lookup by @yczhang-nv in https://github.com/NVIDIA/NeMo-Agent-Toolkit/pull/1948
• fix(mcp): Fix MCP…