Skip to content

CHANGELOG.md

Latest commit

 

History

History
1127 lines (1085 loc) · 130 KB

CHANGELOG.md

File metadata and controls

1127 lines (1085 loc) · 130 KB
Raw

Changelog

All notable changes to this project will be documented in this file.

[1.4.1] - 2026-02-09

🐛 Bug Fixes

  • fix(serve): ensure a single event loop for python 3.11 by @willkill07 in NVIDIA#1558

📚 Documentation

  • Document new nat serve CLI flags by @dagardner-nv in NVIDIA#1562

Full Changelog: https://github.com/NVIDIA/NeMo-Agent-Toolkit/compare/v1.4.0...v1.4.1

[1.4.0] - 2026-02-02

🚀 Notable Features and Improvements

  • LangGraph Agent Automatic Wrapper: Easily onboard existing LangGraph agents to NeMo Agent Toolkit. Use the automatic wrapper to access NeMo Agent Toolkit advanced features with very little modification of LangGraph agents.
  • Automatic Reinforcement Learning (RL): Improve your agent quality by fine-tuning open LLMs to better understand your agent's workflows, tools, and prompts. Perform GRPO with OpenPipe ART or DPO with NeMo Customizer using NeMo Agent Toolkit built-in evaluation system as a verifier.
  • Initial NVIDIA Dynamo Integration: Accelerate end-to-end deployment of agentic workflows with initial Dynamo support. Utilize the new agent-aware router to improve worker latency by predicting future agent behavior.
  • A2A Support: Build teams of distributed agents using the A2A protocol.
  • NeMo Agent Toolkit Safety and Security: Strengthen safety and security of workflows by simulating scenario-based attacks, profiling risk, running guardrail-ready evaluations, and applying defenses with red teaming. Validate defenses, profile risk, monitor behavior, and harden agents across any framework.
  • Amazon Bedrock AgentCore and Strands Agents Support: Build agents using Strands Agents framework and deploy them securely on Amazon Bedrock AgentCore runtime.
  • Microsoft AutoGen Support: Build agents using the Microsoft AutoGen framework.
  • Per-User Functions: Use per-user functions for deferred instantiation, enabling per-user stateful functions, per-user resources, and other features.

🚨 Breaking Changes

  • Update weave trace identifiers by @dagardner-nv in NVIDIA#1055
  • feat: switch calculator functions to a single function group by @willkill07 in NVIDIA#954
  • Use Pydantic SecretStr fields for all sensitive values by @dagardner-nv in NVIDIA#1123
  • Migrate Zep Cloud integration from v2 to v3 API by @jackaldenryan in NVIDIA#1122
  • feat!(llm): exclude unset fields in model dump for all LLMs and Embedders by @willkill07 in NVIDIA#1143
  • Documentation Restructure by @dagardner-nv in NVIDIA#1231
  • Implement Per-User Function Instantiation by @yczhang-nv in NVIDIA#1206
  • Remove default_user_id from GeneralConfig to prevent unsafe per-user workflow sharing by @yczhang-nv in NVIDIA#1282
  • chore: update dependency package versions for 1.4 by @willkill07 in NVIDIA#1316
  • improvement: change Function Group separator to __ by @willkill07 in NVIDIA#1328
  • Refactor MCP Frontend: Move to nvidia-nat-mcp package by @AnuradhaKaruppiah in NVIDIA#1332
  • chore: update nvidia-nat-all and add documentation by @willkill07 in NVIDIA#1340

✨ New Features

  • Add DBNL Telemetry Exporter by @dbnl-renaud in NVIDIA#1111
  • Add default Phoenix session tracking support by @ericevans-nv in NVIDIA#1132
  • Add support for workflow configuration inheritance by @thepatrickchin in NVIDIA#1152
  • Add Middleware and native support for FunctionMiddleware for all functions by @dnandakumar-nv in NVIDIA#1130
  • Add support for a customizable MCP service account auth provider by @AnuradhaKaruppiah in NVIDIA#1176
  • Introduce vanna text2sql by @jiaxiangr in NVIDIA#974
  • Strands integration by @ronjer30 in NVIDIA#1063
  • NAT A2A Client & Server Support by @AnuradhaKaruppiah in NVIDIA#1147
  • Introduce Finetuning Harness for In-Situ Reinforcement Learning of Agentic Workflows by @dnandakumar-nv in NVIDIA#1221
  • Add Support for NeMo Customizer to Finetuning Harness by @dnandakumar-nv in NVIDIA#1241
  • Register per-user ReAct agent by @yczhang-nv in NVIDIA#1274
  • dynamo llm integration with examples, analysis, and custom predictive routers by @bbednarski9 in NVIDIA#1242
  • Add a bridge between NAT and A2A auth mechanisms by @AnuradhaKaruppiah in NVIDIA#1232
  • Migrate the a2a client implementation to per-user mode by @AnuradhaKaruppiah in NVIDIA#1281
  • Add weave feedback integration for chat interactions by @thepatrickchin in NVIDIA#781
  • Extend Middleware interface with pre/post invoke hooks and add DynamicFunctionMiddleware by @ericevans-nv in NVIDIA#1216
  • Agent Safety And Security Engine by @ericevans-nv in NVIDIA#1262
  • Microsoft Autogen Framework Integration [Synopsys] by @bbednarski9 in NVIDIA#1330
  • Implement per-user resource usage monitoring endpoint by @yczhang-nv in NVIDIA#1280
  • Add automatic wrappers for LangGraph Agents by @mdemoret-nv in NVIDIA#1322
  • Make All CLI Commands Plugin-Discoverable by @AnuradhaKaruppiah in NVIDIA#1346
  • feat: Add AutoMemoryWrapper agent for automatic memory management by @jackaldenryan in NVIDIA#1137
  • Add health endpoint to FastAPI server by @antoniomtz in NVIDIA#1466

🔧 Improvements

  • Add a configurable memory profiler for the MCP frontend by @AnuradhaKaruppiah in NVIDIA#961
  • Optimize retry logic with memory management improvements by @dnandakumar-nv in NVIDIA#1014
  • Refactor to make model_name an optimizable field across LLMs by @dnandakumar-nv in NVIDIA#1020
  • Added new agent and example utilizing the OpenAI Responses API by @dnandakumar-nv in NVIDIA#414
  • Include input and output messages in weave observability traces by @thepatrickchin in NVIDIA#1050
  • Allow attaching arbitrary attributes to Weave traces by @dagardner-nv in NVIDIA#1057
  • feat: nat optimizer support for Optuna GridSearch by @bbednarski9 in NVIDIA#1076
  • Lint fixes by @dagardner-nv in NVIDIA#1097
  • Make the run_workflow method a part of the core API by @dagardner-nv in NVIDIA#1098
  • Support Redis password authentication by @dagardner-nv in NVIDIA#1110
  • Update example notebook to use the run_workflow function by @dagardner-nv in NVIDIA#1113
  • Add E2E tests for Simple RAG Example by @dagardner-nv in NVIDIA#1114
  • Add E2E test for ADK demo example by @dagardner-nv in NVIDIA#1115
  • Cleanup E2E tests by @dagardner-nv in NVIDIA#1116
  • Update password fields to use Pydantic SecretStr type by @dagardner-nv in NVIDIA#1118
  • Update fastapi version by @AnuradhaKaruppiah in NVIDIA#1117
  • Support custom MCP server implementations by @AnuradhaKaruppiah in NVIDIA#1087
  • Add reference to NAT job_id in Weave evaluation attributes by @thepatrickchin in NVIDIA#1140
  • Add evaluator reasoning to Weave score logs by @thepatrickchin in NVIDIA#1141
  • Add E2E tests for notebook examples by @dagardner-nv in NVIDIA#1128
  • Add E2E test for simple auth example by @dagardner-nv in NVIDIA#1148
  • Support Unix shell-style wildcards in dataset filter configuration by @thepatrickchin in NVIDIA#1146
  • Add optional TTL configuration for Redis object store by @thepatrickchin in NVIDIA#1157
  • Local sandbox improvements by @dagardner-nv in NVIDIA#1162
  • Forward merge 'release/1.3' into develop by @willkill07 in NVIDIA#1135
  • feat: relax temperature bounds to be model-specific by @willkill07 in NVIDIA#1172
  • Update the test_lifetime_task_timeout test to not take 60s by @dagardner-nv in NVIDIA#1171
  • Ensure that the compatibility loader is removed after each test by @dagardner-nv in NVIDIA#1177
  • Add an E2E test for Simple Calculator Galileo observability example by @dagardner-nv in NVIDIA#1095
  • Improve haystack_deep_research_agent example by @mpangrazzi in NVIDIA#1170
  • Add a simple evaluate_item endpoint by @AnuradhaKaruppiah in NVIDIA#1138
  • Remove work-around for qdrant/qdrant-client#983 by @dagardner-nv in NVIDIA#1186
  • Provide a method for adding routes at the root level of the NAT-MCP server by @AnuradhaKaruppiah in NVIDIA#1187
  • Silence warnings being emitted during tests by @dagardner-nv in NVIDIA#1189
  • Work-around slow import issue for google-adk by @dagardner-nv in NVIDIA#1192
  • Remove pytest-pretty by @dagardner-nv in NVIDIA#1193
  • Add E2E test for RagaAI Catalyst by @dagardner-nv in NVIDIA#1194
  • Create TTC Functions for Multi-LLM Generation by @dnandakumar-nv in NVIDIA#1203
  • Add a Kaggle MCP usage example by @AnuradhaKaruppiah in NVIDIA#1209
  • Security and Lint updates for AgentCore Deploy by @BuildOnCloud in NVIDIA#1220
  • Add a tabular output for evaluation results by @AnuradhaKaruppiah in NVIDIA#1239
  • Update finetuning docs and add harness to workflows guide by @dnandakumar-nv in NVIDIA#1245
  • Update README for RL Example by @dnandakumar-nv in NVIDIA#1252
  • Mark wheels with a beta tag as ready by @dagardner-nv in NVIDIA#1284
  • fix: uv.lock update for nat_react_benchmark_agent by @bbednarski9 in NVIDIA#1285
  • Add rules to try and catch a bug where default='' is used for a SecretStr field by @dagardner-nv in NVIDIA#1304
  • dynamo unit test patch and cleanup by @bbednarski9 in NVIDIA#1303
  • fix: AWS AgentCore IAM policy rules and example prerequisites by @bbednarski9 in NVIDIA#1315
  • Update copyright year by @dagardner-nv in NVIDIA#1317
  • Fix: add parent-child lineage to trace/span exporter attributes by @bbednarski9 in NVIDIA#1320
  • changed to simplified system prompt and properly handle no inputs by @mnajafian-nv in NVIDIA#1307
  • Add configurable description for sequential executor by @thepatrickchin in NVIDIA#1293
  • Add early exit mechanisms for Sequential Executor by @thepatrickchin in NVIDIA#1289
  • chore: bump github actions version to v6 by @willkill07 in NVIDIA#1334
  • Implement Non-session-aware Per-user MCPClient by @yczhang-nv in NVIDIA#1253
  • Add Configuration Preservation to Evaluation Output by @AnuradhaKaruppiah in NVIDIA#1336
  • chore: bump langchain deps; regenerate uv.lock by @willkill07 in NVIDIA#1333
  • Remove stray file unintentionally added to the repository by @dagardner-nv in NVIDIA#1339
  • Rename Sequential Executor input parameter for compatibility with generate endpoints by @thepatrickchin in NVIDIA#1291
  • Implement CLI Plugin Discovery System by @AnuradhaKaruppiah in NVIDIA#1341
  • Improve Safety and Security Engine README by @ericevans-nv in NVIDIA#1344
  • Add documentation specific rules to .coderabbit.yaml by @dagardner-nv in NVIDIA#1348
  • Improves finetuning end status logging by @dnandakumar-nv in NVIDIA#1350
  • chore: update NAT UI submodule by @willkill07 in NVIDIA#1352
  • Update the build_wheel CI stage to always build wheels with matching version dependencies by @dagardner-nv in NVIDIA#1343
  • Update langsmith.xlsx to match data in langsmith.csv by @dagardner-nv in NVIDIA#1360
  • Clean up SWE-bench example: Remove unmaintained predictor and migrate to remote datasets by @AnuradhaKaruppiah in NVIDIA#1361
  • chore: update ui submodule, semantic-kernel, and langchain versions by @willkill07 in NVIDIA#1369
  • Reorganize A2A Examples for Clarity by @AnuradhaKaruppiah in NVIDIA#1368
  • add support for langchain agents that are wrapped as async context managers by @gfreeman-nvidia in NVIDIA#1371
  • chore: bump urllib3+langchain; specify werkzeug as transitive dep by @willkill07 in NVIDIA#1375
  • chore: speed up tests by @willkill07 in NVIDIA#1378
  • Decouple HuggingFace LLM provider from LangChain dependency by @ericevans-nv in NVIDIA#1367
  • Add code owners for example data directories by @dagardner-nv in NVIDIA#1379
  • Fix Windows path parsing in find_package_root by @ericevans-nv in NVIDIA#1380
  • chore: update nvidia_nat_weave > weave > fickling dependency by @willkill07 in NVIDIA#1386
  • Add a pre-commit script to ensure output cells of notebooks are cleared by @dagardner-nv in NVIDIA#1381
  • Increase the time limit for the test stage by @dagardner-nv in NVIDIA#1400
  • Expose Dask memory_limit config by @dagardner-nv in NVIDIA#1401
  • Standardize RAG service response schema parsing by @ericevans-nv in NVIDIA#1406
  • Fix/simplify event loop test by @mnajafian-nv in NVIDIA#1405
  • fix: correct ReWOO planner prompt JSON example format by @mnajafian-nv in NVIDIA#1410
  • Add pytest-timeout and set a global 5min timeout by @dagardner-nv in NVIDIA#1411
  • Expose Dask threads per worker by @dagardner-nv in NVIDIA#1408
  • Handle consecutive status check failures with retry logic in DPO trainer adapter by @dnandakumar-nv in NVIDIA#1415
  • Fix multi_frameworks workflow CI failure by @mnajafian-nv in NVIDIA#1418
  • Update middleware to use FunctionGroup.SEPARATOR for function matching by @ericevans-nv in NVIDIA#1448
  • Update A2A docs by @AnuradhaKaruppiah in NVIDIA#1447
  • Update the build_wheel CI script to test that built wheels are installable by @dagardner-nv in NVIDIA#1457
  • Add websocket MCP auth check script (no UI) by @AnuradhaKaruppiah in NVIDIA#1465
  • docs: Restore Llama config docs in simple_web_query_eval README by @mnajafian-nv in NVIDIA#1472
  • fix: dynamo multi-worker deployment shell script update by @bbednarski9 in NVIDIA#1479
  • update package versions in uv.lock; update UI submodule by @willkill07 in NVIDIA#1469
  • Update Dask by @dagardner-nv in NVIDIA#1478
  • Improve Safety and Security retail agent docs by @ericevans-nv in NVIDIA#1492
  • improvement(adk-example): update example to prefer NVIDIA NIM by @willkill07 in NVIDIA#1495
  • add name attribute to FunctionBaseConfig for workflow naming in span exporter by @bbednarski9 in NVIDIA#1482
  • chore: prefer non-required packages are manually installed by @willkill07 in NVIDIA#1516
  • chore: remove huggingface extra by @willkill07 in NVIDIA#1525

🐛 Bug Fixes

  • Ensure CI uses --first-parent when calling git describe by @dagardner-nv in NVIDIA#940
  • Fixes to detect optional parameters in tool conversion used by "nat mcp serve" by @AnuradhaKaruppiah in NVIDIA#1126
  • Mini Patch ReWOO Test Failure by @billxbf in NVIDIA#1155
  • Fix documentation version switcher by @thepatrickchin in NVIDIA#1159
  • Ensure that the ADKProfilerHandler patches are not applied more than once by @dagardner-nv in NVIDIA#1175
  • Fix documentation_checks.sh script to run on MacOS by @dagardner-nv in NVIDIA#1178
  • Add bind_tools and bind methods to LangChainTestLLM by @AnuradhaKaruppiah in NVIDIA#1181
  • Truncate long error messages by @dagardner-nv in NVIDIA#1182
  • Ensure jq is installed prior to running integration tests by @dagardner-nv in NVIDIA#1183
  • fix(azure-openai): ensure api_version is specified by @willkill07 in NVIDIA#1185
  • Replace nest-asyncio with nest-asyncio2 by @dagardner-nv in NVIDIA#1190
  • Bug/strands unit tests by @bbednarski9 in NVIDIA#1196
  • Fix: Add ca-certificates to simple_calculator Dockerfile by @rmalani-nv in NVIDIA#1201
  • Use secret value for client_secret in OAuth client by @dzmitryv111111 in NVIDIA#1198
  • Fix the aiq_compatibility_span_prefix fixture by @dagardner-nv in NVIDIA#1199
  • Add model_name as a computed field to AzureOpenAIModelConfig by @dagardner-nv in NVIDIA#1214
  • Enable observability for individual function calls in MCP server by @mpenn in NVIDIA#1234
  • Update the nvidia-nat-vanna dependency on nvidia-nat to declare plugins using the square bracket form by @dagardner-nv in NVIDIA#1238
  • Use a local Piston server for E2E integration tests by @dagardner-nv in NVIDIA#1244
  • Fix ReAct agent TypeError with LiteLLM and Anthropic models by @sjarmak in NVIDIA#1251
  • Adopt fixes for image generation by @dagardner-nv in NVIDIA#1286
  • Unify the user_id adding logic to context_state for multiple CLI commands by @yczhang-nv in NVIDIA#1287
  • Fix MCP workflow entry function handling by @mpenn in NVIDIA#1277
  • Fix bug where SecretStr fields defaulting to an empty string were not being instantiated by @dagardner-nv in NVIDIA#1298
  • Fix TypeConverter not able to handle Union type conversion by @yczhang-nv in NVIDIA#1301
  • Revert version specification to 1.4 by @willkill07 in NVIDIA#1312
  • Change the url field in ImageUrl model from HttpUrl to str by @mpenn in NVIDIA#1314
  • Add error handling to E2E test report script by @dagardner-nv in NVIDIA#1319
  • Fix notebook E2E tests by @dagardner-nv in NVIDIA#1321
  • Update openpipe-art to version 0.5.4 by @dnandakumar-nv in NVIDIA#1323
  • Fix simple_calculator protected a2a server installation issues by @AnuradhaKaruppiah in NVIDIA#1326
  • Improve Multi-User Testing Instructions in Math Assistant A2A Example by @AnuradhaKaruppiah in NVIDIA#1329
  • Resolve dependency conflicts from nvidia_nat_openpipe_art package by @dagardner-nv in NVIDIA#1331
  • Add missing tzdata package to Docker image by @dagardner-nv in NVIDIA#1337
  • Fix CI failures: RAG recursion and eval assertion by @mnajafian-nv in NVIDIA#1347
  • Fix A2A Client CLI Commands After Multi-User Migration by @AnuradhaKaruppiah in NVIDIA#1353
  • Revert system prompt for react agent's prompt by @mnajafian-nv in NVIDIA#1358
  • fix: strip remaining occurrences of . for function groups by @willkill07 in NVIDIA#1362
  • Update weave to latest version, resolves a conflict with autogen by @dagardner-nv in NVIDIA#1363
  • Update FunctionGroup separator in MCP client CLI by @yczhang-nv in NVIDIA#1359
  • Fix training cancellation 404 error by @mnajafian-nv in NVIDIA#1364
  • chore: ensure all installable examples are specified in root pyproject.toml by @willkill07 in NVIDIA#1373
  • For tagged and nightly builds use GIT_TAG as-is by @dagardner-nv in NVIDIA#1376
  • bug fix: Dynamo SGLang Startup Script Cleanup by @bbednarski9 in NVIDIA#1357
  • fix: Amd64 Support for Bedrock Strands Demo by @bbednarski9 in NVIDIA#1377
  • Update currency agent A2A example instructions to use openai models by @AnuradhaKaruppiah in NVIDIA#1372
  • fix: langchain<>huggingface integration by @willkill07 in NVIDIA#1382
  • Async endpoint improvements by @dagardner-nv in NVIDIA#1374
  • Fix/agno flaky test release 1.4 by @mnajafian-nv in NVIDIA#1383
  • fix: update config_inheritance example with proper setup by @willkill07 in NVIDIA#1384
  • fix: update configs for autogen example; fix MCP tool wrapping by @willkill07 in NVIDIA#1387
  • Fix nvbug: SSL cert verification and FD exhaustion in email_phishing_analyzer Docker build by @mnajafian-nv in NVIDIA#1389
  • Fix issues with haystack deep research agent example by @dagardner-nv in NVIDIA#1388
  • Update help string and doc for "nat run --input_file" by @AnuradhaKaruppiah in NVIDIA#1390
  • autogen demo: LA traffic example by @bbednarski9 in NVIDIA#1426
  • Update test models to nemotron 3 and fix test assertions by @hsin-c in NVIDIA#1425
  • Re-generate several dataset in examples by @yczhang-nv in NVIDIA#1427
  • fix(oauth2): Add client_id to refresh_token request for MaaS OAuth servers by @andywy110 in NVIDIA#1421
  • Fix token usage statistics and image viewing in Profiler Agent by @dagardner-nv in NVIDIA#1428
  • Update deep research notebook with Nemotron models and clearer instructions by @yczhang-nv in NVIDIA#1436
  • fix(eval): prevent awaited coroutine reuse on Exception by @willkill07 in NVIDIA#1438
  • fix(weave): ensure contextmanager protocol is implemented for weave mock by @willkill07 in NVIDIA#1439
  • fix(deps): version specifiers with major.minor.patch should not use ~= by @willkill07 in NVIDIA#1452
  • Update models and inputs langgraph_deep_research notebook to enhance performance and consistency by @yczhang-nv in NVIDIA#1444
  • Fix MCP tool UI display by @AnuradhaKaruppiah in NVIDIA#1462
  • Fix CI failures: Complete Llama→Nemotron migration for remaining exam… by @mnajafian-nv in NVIDIA#1464
  • Fix concurrent async generate requests by @dagardner-nv in NVIDIA#1498
  • Remove the task_timeout from the a2a sample config files by @AnuradhaKaruppiah in NVIDIA#1508
  • Escape special characters in Redis user_id for vector search by @thepatrickchin in NVIDIA#1494
  • chore: update UI submodule to have latest fixes by @willkill07 in NVIDIA#1522
  • Fix LLM calling actions not traced in phoenix when running nat serve by @yczhang-nv in NVIDIA#1520
  • fix(testing): guard huggingface integration test with importorskip by @willkill07 in NVIDIA#1535

📝 Documentation Updates

  • docs: initial nat optimizer notebook by @bbednarski9 in NVIDIA#1053
  • doc: cleanup notebook 6 (nat optimize) and alert triage agent optimization by @bbednarski9 in NVIDIA#1125
  • docs: getting started notebook 7 - mcp client and server setup using NAT by @bbednarski9 in NVIDIA#1145
  • docs: renumbering the getting started notebooks by @bbednarski9 in NVIDIA#1149
  • Enhance documentation for Strands Agents integration by @ronjer30 in NVIDIA#1205
  • Updates to AWS AgentCore README and scripts by @ronjer30 in NVIDIA#1208
  • google-adk version upgrade by @bbednarski9 in NVIDIA#1217
  • tests: remove obsolete conftest by @bbednarski9 in NVIDIA#1219
  • Restructuring and reorganizing workflows by @lvojtku in NVIDIA#1173
  • Update Cursor rules to use the new naming guidance by @yczhang-nv in NVIDIA#1273
  • Define terms in documentation on first use, and refer back to definition when used in other documents by @dagardner-nv in NVIDIA#1254
  • Add support matrix for RL by @dnandakumar-nv in NVIDIA#1327
  • Update README instructions for consistency and clarity by @dnandakumar-nv in NVIDIA#1338
  • Add documentation compatibility redirects for old 1.3 urls by @dagardner-nv in NVIDIA#1351
  • Update Python version to 3.13 in README example by @dnandakumar-nv in NVIDIA#1366
  • Fix kaggle_mcp example input by @yczhang-nv in NVIDIA#1395
  • docs: fix docker run commands for local LLMs by @willkill07 in NVIDIA#1398
  • Update langchain_deep_research documentation to mention Anthropic API key is needed by @yczhang-nv in NVIDIA#1402
  • docs: add deepwiki badge; update troubleshooting to mention conda by @willkill07 in NVIDIA#1412
  • docs: add complexity levels to all examples by @willkill07 in NVIDIA#1422
  • bug fix: dynamo integration - model download and instructions clarification by @bbednarski9 in NVIDIA#1420
  • Add no cache installation to ART by @dnandakumar-nv in NVIDIA#1424
  • fix: strands demo reliability improvements by @bbednarski9 in NVIDIA#1429
  • docs: nat-dynamo startup scripts improved envar documentation by @bbednarski9 in NVIDIA#1443
  • docs: add conda install warning to installation.md by @bbednarski9 in NVIDIA#1446
  • docs: add CUDA prereq warning to examples by @bbednarski9 in NVIDIA#1455
  • Minor cleanup to Simple Calculator Eval documentation by @dagardner-nv in NVIDIA#1463
  • docs: dynamo readme simplification and hardware requirements cleanup by @bbednarski9 in NVIDIA#1509
  • Update RL README with OpenAI API key setup and adjust commands by @dnandakumar-nv in NVIDIA#1514
  • docs: dynamo integration performance comparison docs by @bbednarski9 in NVIDIA#1515
  • Update documentation for prerequisites and logprobs clarification by @dnandakumar-nv in NVIDIA#1530
  • docs: add migration guide for 1.4 by @willkill07 in NVIDIA#1533
  • docs: 1.4 changelog and release notes by @willkill07 in NVIDIA#1544
  • Update README for 1.4 Release by@mdemoret-nv in NVIDIA#1546

🙌 New Contributors

  • @dbnl-renaud made their first contribution in NVIDIA#1111
  • @mpangrazzi made their first contribution in NVIDIA#1170
  • @jiaxiangr made their first contribution in NVIDIA#974
  • @ronjer30 made their first contribution in NVIDIA#1063
  • @rmalani-nv made their first contribution in NVIDIA#1201
  • @dzmitryv111111 made their first contribution in NVIDIA#1198
  • @BuildOnCloud made their first contribution in NVIDIA#1220
  • @sjarmak made their first contribution in NVIDIA#1251
  • @andywy110 made their first contribution in NVIDIA#1421

[1.3.1] - 2025-11-07

📦 Overview

This is a minor release with documentation updates, bug fixes, and non-breaking improvements.

✨ New Features

  • feat: Add claude-sonnet-4.5 support by model-gating top_p by @willkill07 in NVIDIA#1134
  • Add support for arbitrary JSON body types in custom routes by @ericevans-nv in NVIDIA#1163

🐛 Bug Fixes

  • bug: fix non json serializable objects in config by @bbednarski9 in NVIDIA#1112
  • fix ADK demo multi-user session by @antoniomtz in NVIDIA#1120
  • Fixes to detect optional parameters in tool conversion used by "nat mcp serve" by @willkill07 in NVIDIA#1133
  • Async Chat fixes by @dagardner-nv in NVIDIA#1131
  • Fix code concatenation issue with code_execution_tool when using a Piston server by @dagardner-nv in NVIDIA#1154
  • Fix documentation version switcher by @willkill07 in NVIDIA#1167

📝 Documentation Updates

  • Misc Documentation Fixes by @dagardner-nv in NVIDIA#1136
  • Document the need to install nvidia-nat-test prior to using ToolTestRunner by @dagardner-nv in NVIDIA#1150
  • Update reasoning diagrams by @dagardner-nv in NVIDIA#1153
  • Update Quick Start UI documentation by @ericevans-nv in NVIDIA#1156
  • Add security-considerations.md document by @dagardner-nv in NVIDIA#1168
  • docs: 1.3.1 changelog by @willkill07 in NVIDIA#1166

🙌 New Contributors

  • @antoniomtz made their first contribution in NVIDIA#1120

[1.3.0] - 2025-10-24

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

✨ New Features

  • Add features nat workflow create a versioned dependency and data and symlinks folder by @zhongxuanwang-nv in NVIDIA#639
  • Feature: Azure OpenAI LLM provider and client by @willkill07 in NVIDIA#643
  • Timezone Support for datetime Tool and Normalize Response Time Handling by @zhongxuanwang-nv in NVIDIA#660
  • Feature: GPT-5 Support by @willkill07 in NVIDIA#664
  • Customize Log Truncation in Config by @RohanAdwankar in NVIDIA#723
  • feat: Support for Nemotron thinking configuration by @willkill07 in NVIDIA#717
  • Track agent system prompt in config and add config to skip maintenance check by @hsin-c in NVIDIA#724
  • Add nvidia-nat-data-flywheel subpackage with NeMo Data Flywheel integrations by @mpenn in NVIDIA#716
  • Enhance ProcessingExporter system to support redaction of content in telemetry traces by @mpenn in NVIDIA#751
  • feat: Python 3.13 support by @willkill07 in NVIDIA#761
  • Add test LLM provider to support testing by @zhongxuanwang-nv in NVIDIA#764
  • Support additional provider parameters in LLM and Embedder config by @YosiElias in NVIDIA#749
  • Add return_direct option to tool_calling_agent for direct tool responses by @thepatrickchin in NVIDIA#775
  • Enable MCP auth for NAT MCP clients by @AnuradhaKaruppiah in NVIDIA#752
  • Add function group filtering by @willkill07 in NVIDIA#807
  • Implement Sequential Executor tool by @yczhang-nv in NVIDIA#806
  • Add a /debug route to NAT MCP frontend to expose MCP tools by @zhongxuanwang-nv in NVIDIA#813
  • MCP OAuth2 Token Introspection Validator by @ericevans-nv in NVIDIA#809
  • [Synopsys] Feature: Google ADK Integration by @saglave in NVIDIA#726
  • Add a blueprint for Haystack Deep Research Agent by @oryx1729 in NVIDIA#461
  • fix: re-add litellm after accidental removal by @willkill07 in NVIDIA#852
  • Add mcp/client/tool/list endpoint by @yczhang-nv in NVIDIA#853
  • feat: LiteLLM support for LangChain/LangGraph, Agno, CrewAI, LlamaIndex by @willkill07 in NVIDIA#881
  • Add configurable token storage to MCP auth by @yczhang-nv in NVIDIA#883
  • feat: Improve the developer journey for example notebooks by @willkill07 in NVIDIA#912
  • feat: Add .env loading support to NAT cli by @willkill07 in NVIDIA#952
  • feat: make built-in agents input adaptable by @willkill07 in NVIDIA#959
  • UI submodule update 1.3 by @ericevans-nv in NVIDIA#1002
  • feat: switch to nemotron reasoning models by @willkill07 in NVIDIA#1036

🔧 Improvements

  • Collapse the docs dependency group into the dev dependencies group by @dagardner-nv in NVIDIA#591
  • Forward-merge release/1.2 into develop by @dagardner-nv in NVIDIA#679
  • Forward-merge release/1.2 into develop by @dagardner-nv in NVIDIA#690
  • Weave: Group workflow traces under the parent evaluation call by @AnuradhaKaruppiah in NVIDIA#663
  • Misc release script improvements by @dagardner-nv in NVIDIA#692
  • Fix pytest fixture deprecation warning by @willkill07 in NVIDIA#698
  • Adopt ruff in CI by @dagardner-nv in NVIDIA#694
  • Upload test results to codecov by @dagardner-nv in NVIDIA#699
  • Add Coderabbit config by @dagardner-nv in NVIDIA#710
  • Allow custom post-processing of EvalInput after the workflow is run by @AnuradhaKaruppiah in NVIDIA#701
  • Adding a Needs Triage label to issues which are created externally by @mdemoret-nv in NVIDIA#700
  • Add fixtures allowing e2e tests to be optionally skipped upon missing environment variables by @dagardner-nv in NVIDIA#720
  • Enable running e2e tests for nightly CI by @dagardner-nv in NVIDIA#727
  • Enable the forward merger plugin of the rapids ops bot by @dagardner-nv in NVIDIA#728
  • Ensure error reporting and propagating in a consistent pattern by @yczhang-nv in NVIDIA#722
  • Improve input normalization of ReAct agent by @yczhang-nv in NVIDIA#730
  • Update version of numpy to be more recent by @zhongxuanwang-nv in NVIDIA#746
  • chore: update LangChain and LangGraph versions by @willkill07 in NVIDIA#780
  • Refactor OTLPSpanHeaderRedactionAdapterExporter to support multiple headers and Span tags by @mpenn in NVIDIA#767
  • Require approval from the nat-dep-approvers group for dependency changes by @dagardner-nv in NVIDIA#782
  • Add tool_call_max_retries option to ReWOO agent by @yczhang-nv in NVIDIA#785
  • Add NAT Agent Hyperparameter Optimizer by @dnandakumar-nv in NVIDIA#650
  • Deprecating use_uvloop from general section of the config. by @zhongxuanwang-nv in NVIDIA#794
  • Report nightly test results by @dagardner-nv in NVIDIA#797
  • Expanding nightly E2E tests by @dagardner-nv in NVIDIA#812
  • Move MCP Client functionality to function groups by @AnuradhaKaruppiah in NVIDIA#814
  • Add raise_tool_call_error option to ReWOO agent by @yczhang-nv in NVIDIA#819
  • Improved Dask shutdown by @dagardner-nv in NVIDIA#825
  • fix: improve Google ADK structure and fix callback handlers for tools and LLMs by @willkill07 in NVIDIA#848
  • Skip some tests in test_mcp_client_base.py to avoid blocking CI by @yczhang-nv in NVIDIA#850
  • Implement OAuth2 security test coverage by @ericevans-nv in NVIDIA#862
  • Console Auth Flow Exception Improvement by @ericevans-nv in NVIDIA#867
  • Simplify simple-calculator MCP example by @AnuradhaKaruppiah in NVIDIA#874
  • ReWOO typing enhancements; more ruff checks; prefer langchain-tavily by @willkill07 in NVIDIA#872
  • Mandate user id for MCP oauth2 authentication by @AnuradhaKaruppiah in NVIDIA#873
  • chore: bump nat-ui submodule by @willkill07 in NVIDIA#876
  • Add additional E2E tests for examples by @dagardner-nv in NVIDIA#849
  • Include branch name in nightly test report by @dagardner-nv in NVIDIA#879
  • Improve new workflow template by @zhongxuanwang-nv in NVIDIA#851
  • Enhance OpenAI Chat API Compatibility by @ericevans-nv in NVIDIA#889
  • chore: additional workflow template cleanup by @willkill07 in NVIDIA#899
  • Add hierarchical IDs for consistent telemetry and reporting by @zhongxuanwang-nv in NVIDIA#863
  • Perform vale spelling checks on notebooks by @dagardner-nv in NVIDIA#896
  • Implement deprecated decorator for deprecation notices by @AnuradhaKaruppiah in NVIDIA#904
  • Implement session aware MCP client routing by @AnuradhaKaruppiah in NVIDIA#898
  • feat: Improve the developer journey for example notebooks (part 2) by @willkill07 in NVIDIA#913
  • Set the title warning to an error by @dagardner-nv in NVIDIA#918
  • Improve multi-user MCP client handling by @AnuradhaKaruppiah in NVIDIA#922
  • Avoid Pydantic serialization warning triggered by tests by @dagardner-nv in NVIDIA#925
  • fix: haystack deep research agent must be part of examples by @willkill07 in NVIDIA#927
  • Silence several warnings being emitted by the tests by @dagardner-nv in NVIDIA#928
  • UI submodule update by @ericevans-nv in NVIDIA#932
  • Add ADK to TestLLM by @zhongxuanwang-nv in NVIDIA#937
  • Add opensearch service to CI by @dagardner-nv in NVIDIA#944
  • Add an integration test for the custom route front-end example by @dagardner-nv in NVIDIA#945
  • fix: move Google ADK agent example back to ADK example by @willkill07 in NVIDIA#943
  • Add a docker compose yaml for running integration tests by @dagardner-nv in NVIDIA#946
  • Clean up MCP logs by @AnuradhaKaruppiah in NVIDIA#957
  • Limit when we upload to artifactory by @dagardner-nv in NVIDIA#965
  • Add security related warnings to MCP auth documentation by @yczhang-nv in NVIDIA#979
  • Add E2E test for the simple calculator HITL example by @dagardner-nv in NVIDIA#984
  • Add additional E2E tests for examples by @dagardner-nv in NVIDIA#986
  • Add an E2E test for the simple calculator MCP example by @dagardner-nv in NVIDIA#990
  • Add E2E test for Redis Memory example by @dagardner-nv in NVIDIA#994
  • Enable Chat History for WebSocket Messages by @ericevans-nv in NVIDIA#999
  • fix: explicitly add tool.uv.managed = true to pyproject.toml files by @willkill07 in NVIDIA#1003
  • fix: address coderabbit feedback given from forward merge PR by @willkill07 in NVIDIA#1007
  • Fix string concatenation by @zhongxuanwang-nv in NVIDIA#995
  • Update backend corresponding to the MCP UI changes by @AnuradhaKaruppiah in NVIDIA#988
  • Add E2E tests for Simple Calculator Observability example by @dagardner-nv in NVIDIA#1019
  • fix: update authlib by @willkill07 in NVIDIA#1017
  • feat: unify wording for agent docs; clarify local LLMs; update telemetry package by @willkill07 in NVIDIA#1042
  • Always perform wheel builds in nightly CI by @dagardner-nv in NVIDIA#1046
  • docs: getting started notebook no. 1-5 cleanup by @bbednarski9 in NVIDIA#1039
  • fix: reintroduce --all-files to pre-commit CI by @willkill07 in NVIDIA#1048
  • Add E2E test for Langfuse observability example by @dagardner-nv in NVIDIA#1047
  • Refactor Optimizer Documentation for Clarity by @dnandakumar-nv in NVIDIA#1026
  • Move pareto visualzation section to docs from example by @dnandakumar-nv in NVIDIA#1064
  • Add location for prompt optimization functions by @dnandakumar-nv in NVIDIA#1077
  • Fix WebSocket HITL Response Schema and Update UI Submodule by @ericevans-nv in NVIDIA#1079
  • Add E2E test for Simple Calculator LangSmith observability example by @dagardner-nv in NVIDIA#1083
  • feat(mcp): allow MCP Server --tool_name filter to reference function groups by @willkill07 in NVIDIA#1093
  • Add gRPC Protocol Support to OTLP Span Exporters by @mpenn in NVIDIA#1102

🐛 Bug Fixes

  • Toolcalling prompt by @gfreeman-nvidia in NVIDIA#617
  • Fix missing f-string prefixes in error messages by @YosiElias in NVIDIA#686
  • Configure setuptools_scm to use the --first-parent flag by @dagardner-nv in NVIDIA#693
  • Persist User Message ID For HTTP Connections by @ericevans-nv in NVIDIA#696
  • fix(pytest): suppress upstream pydantic warning from mem0 by @willkill07 in NVIDIA#709
  • fix(ModelGatedFieldMixin): support multiple and indirect inheritance; rename to GatedFieldMixin by @willkill07 in NVIDIA#707
  • Configure coderabbit not to apply conflicting labels by @dagardner-nv in NVIDIA#714
  • Add missing implementation of abstract methods of ToolTestRunner by @yczhang-nv in NVIDIA#729
  • fix: Improved model detection/rules for ThinkingMixin by @willkill07 in NVIDIA#733
  • Set StreamHandler to use sys.stdout in console registered logging method by @mpenn in NVIDIA#742
  • Add observability support when using MCP front end by @mpenn in NVIDIA#741
  • Fix issues in GPU Sizing Launchable Notebook by @nv-edwli in NVIDIA#747
  • fix(llm): resolve patch order to apply retry before thinking by @willkill07 in NVIDIA#750
  • Remove conflicting/redundant langchain-milvus deps by @dagardner-nv in NVIDIA#754
  • Update weave to 0.52 to handle incompat with gql 4.0.0 by @AnuradhaKaruppiah in NVIDIA#755
  • fix: include thinking in model_dump for serve config serialization by @willkill07 in NVIDIA#771
  • Update MCP client readme to use the streamable-http example by @AnuradhaKaruppiah in NVIDIA#777
  • Fix async endpoints when using multiple workers by @dagardner-nv in NVIDIA#725
  • fix: ensure model_dump excludes None fields when appropriate by @willkill07 in NVIDIA#772
  • Fix workflow create documentation and command by @dagardner-nv in NVIDIA#790
  • Fix run_ci_local.sh to not prompt for username/password by @dagardner-nv in NVIDIA#792
  • Fix NAT FastAPI front end with Stdio-MCP server fails to initialize by @zhongxuanwang-nv in NVIDIA#788
  • Enable agent optimizer and refine LangChain callback handling. by @dnandakumar-nv in NVIDIA#796
  • fix(cli): nat workflow create should validate workflow name by @Akshat8510 in NVIDIA#787
  • Fix issue where optimizable params are in model dump by @dnandakumar-nv in NVIDIA#801
  • Prevent retry storms in nested method calls by @dnandakumar-nv in NVIDIA#803
  • Fix the test_unified_api_server integration tests by @dagardner-nv in NVIDIA#804
  • Fixes chat_completion returning wrong type and substitute .content with .text() by @zhongxuanwang-nv in NVIDIA#802
  • Move visualization import into method for Optimizer by @dnandakumar-nv in NVIDIA#810
  • fix: ensure workflows set a FunctionGroups instance_name by @willkill07 in NVIDIA#815
  • Make workflow name and description configurable as MCP tools by @yczhang-nv in NVIDIA#816
  • fix: ensure ContextVars are all properly initialized by @willkill07 in NVIDIA#822
  • Update RedisEditor to retrieve full document data from Redis when using get_memory tool by @thepatrickchin in NVIDIA#823
  • fix: correct logic for test_unified_api_server.py by @willkill07 in NVIDIA#826
  • Fix TraceAdapterRegistry lookup errors in SpanToDFWRecordProcessor by @mpenn in NVIDIA#831
  • Fix test_azure_openai_minimal_agent test by @dagardner-nv in NVIDIA#832
  • Avoid calling 'git lfs install' as CI already performs this by @dagardner-nv in NVIDIA#833
  • Add missing dependencies by @dagardner-nv in NVIDIA#835
  • Enable running tests for examples by @dagardner-nv in NVIDIA#838
  • fix: Ensure console front-end validation is called by @willkill07 in NVIDIA#844
  • Fix tests under examples/, remove all pytest skip markers by @dagardner-nv in NVIDIA#846
  • Fix chat_history processing logic in ReAct agent by @yczhang-nv in NVIDIA#847
  • Improve robustness of MCP client remote tool calling by @yczhang-nv in NVIDIA#840
  • Fix swallowing client errors bug by @zhongxuanwang-nv in NVIDIA#841
  • Declare pip as a direct dependency by @dagardner-nv in NVIDIA#871
  • Improve the re-connect handling mechanism for MCP with auth by @yczhang-nv in NVIDIA#875
  • fix: ensure registration of adk demo functions; reduce warnings by @willkill07 in NVIDIA#885
  • Fix problem with displaying MCP tools via the client CLI commands by @AnuradhaKaruppiah in NVIDIA#888
  • Revert "mcp-client-cli: Note that client and server transports must match." by @AnuradhaKaruppiah in NVIDIA#892
  • Fix Google ADK Demo registration by @willkill07 in NVIDIA#901
  • fix: haystack deep research example test failure by @willkill07 in NVIDIA#910
  • fix: Improve version detection for prerelease workflow creation by @willkill07 in NVIDIA#911
  • fix: TTC must await get_function from builder by @willkill07 in NVIDIA#914
  • fix: Docker must redeclare args in multi-stage builds; fix path in docs by @willkill07 in NVIDIA#916
  • fix: pin uvicorn to prevent nest_asyncio patch error by @willkill07 in NVIDIA#929
  • Resolve cancel scope error in MCP session cleanup with lifetime task by @AnuradhaKaruppiah in NVIDIA#931
  • fix: import error for weave sanitize by @willkill07 in NVIDIA#934
  • fix: add missing awaits for get_memory_client by @willkill07 in NVIDIA#935
  • Update package metadata by @dagardner-nv in NVIDIA#938
  • fix: ensure console logging is configurable by @willkill07 in NVIDIA#947
  • Enable the upload step for the release branches in nightly builds by @dagardner-nv in NVIDIA#953
  • fix: custom plot charts function should error on invalid chart types by @willkill07 in NVIDIA#949
  • Attempt to fix wheel metadata by @dagardner-nv in NVIDIA#958
  • fix: ensure mcp client can load exported function group functions by @willkill07 in NVIDIA#960
  • fix: Dockerfiles must not use any arg expansion on COPY --from lines by @willkill07 in NVIDIA#962
  • fix: tracing in configs, clarify directions for simple web query by @willkill07 in NVIDIA#968
  • Fix profiler agent tests by @dagardner-nv in NVIDIA#969
  • Fix the simple calc hitl example by @dagardner-nv in NVIDIA#970
  • Fix the profiler agent E2E test by @dagardner-nv in NVIDIA#975
  • fix: small changes to improve reliability of getting started notebooks by @bbednarski9 in NVIDIA#989
  • Fix reasoning models ending with v1 to use detailed thinking format by @jiayin-nvidia in NVIDIA#980
  • fix: Update system message (if exists) for thinking injection by @willkill07 in NVIDIA#987
  • fix: improve agent-to-agent calling by simplifying pydantic model by @willkill07 in NVIDIA#993
  • fix: langchain web ingest script must not always add CUDA documents by @willkill07 in NVIDIA#1018
  • Suppress error log generated when terminating NAT MCP server with ctrl + C by @yczhang-nv in NVIDIA#1022
  • docs: prevent coderabbit from applying common labels by @willkill07 in NVIDIA#1029
  • Fix MCP auth redirect handling for remote-ssh and update docs by @AnuradhaKaruppiah in NVIDIA#1023
  • Fix broken E2E tests by @dagardner-nv in NVIDIA#1033
  • Fixing the repeated step id bug by @zhongxuanwang-nv in NVIDIA#1032
  • fix: update mcp test to not patch multiple times by @willkill07 in NVIDIA#1045
  • Keep original NaN or null scores from LLM judge in eval output by @yczhang-nv in NVIDIA#1058
  • fix: eval integration test should inspect Ragas evaluators by @willkill07 in NVIDIA#1067
  • fix: pin langchain to prevent upgrade by @willkill07 in NVIDIA#1074
  • fix: strip rc package from notebook by @willkill07 in NVIDIA#1081
  • fix: apply coderabbit suggestions from forward merge by @willkill07 in NVIDIA#1089
  • fix: generalize eval test by reducing assumptions by @willkill07 in NVIDIA#1090
  • fix(mcp-client): support anyOf and oneOf when constructing schemas by @willkill07 in NVIDIA#1094
  • fix(rewoo): replace placeholder IFF type is str by @willkill07 in NVIDIA#1105
  • fix(examples-hitl): RetryReactAgent must work with function groups by @willkill07 in NVIDIA#1106

📝 Documentation Updates

🙌 New Contributors

[1.2.1] - 2025-08-20

📦 Overview

This is a documentation only release, there are no code changes in this release.

📜 Full Change Log

[1.2.0] - 2025-08-20

📦 Overview

The NeMo Agent Toolkit, formerly known as Agent Intelligence (AIQ) toolkit, has been renamed to align with the NVIDIA NeMo family of products. This release brings significant new capabilities and improvements across authentication, resource management, observability, and developer experience. The toolkit continues to offer backwards compatibility, making the transition seamless for existing users.

While NeMo Agent Toolkit is designed to be compatible with the previous version, users are encouraged to update their code to follow the latest conventions and best practices. Migration instructions are provided in the migration guide.

🚨 Breaking Changes

🚀 Notable Features and Improvements

  • Authentication for Tool Calling: Implement robust authentication mechanisms that enable secure and configurable access management for tool invocation within agent workflows.
  • Test Time Compute: Dynamically reallocate compute resources after model training, allowing agents to optimize reasoning, factual accuracy, and system robustness without retraining the base model.
  • Sizing Calculator: Estimate GPU cluster requirements to support your target number of users and desired response times, simplifying deployment planning and scaling.
  • Object Store Integration: Connect and manage data through supported object stores, improving agent extensibility and enabling advanced data workflows.
  • Enhanced Cursor Rules: Build new workflows or extend existing ones by leveraging cursor rules, making agent development faster and more flexible.
  • Interactive Notebooks: Access a suite of onboarding and example notebooks to accelerate agent workflow development, testing, and experimentation.
  • Observability Refactor: Onboard new observability and monitoring platforms more easily, and take advantage of improved plug-in architecture for workflow inspection and analysis.
  • Examples Reorganization: Organize examples by functionality, making it easier to find and use the examples.

📜 Full Change Log

🙌 New Contributors

[1.1.0] - 2025-05-16

Key Features

  • Full MCP (Model Context Protocol) support
  • Weave tracing
  • Agno integration
  • ReWOO Agent
  • Alert Triage Agent Example

What's Changed

New Contributors

[1.1.0a1] - 2025-04-05

Added

  • Added CORS configuration for the FastAPI server
  • Added support for customizing evaluation outputs and uploading results to remote storage

Fixed

  • Fixed aiq serve when running the simple_rag workflow example
  • Added missing platformdirs dependency to aiqtoolkit package

[1.0.0] - 2024-12-04

Added

  • First release.