v1.4.2

Changelog

New Features:

• MCP SSE Support: Added support for connecting to SSE MCP Servers.
• Tool Hooks: You can now have a hook that is wrapped around all tool calls. This works for Toolkits and custom tools. See this example.
• Team Session State: You can now manage a single state dictionary across a team leader and team members inside tools given to the team leader/members. See this example.
• Cartesia Tool: Added support for Cartesia for text-to-speech capabilities.
• Gemini Image Tools: Added a tool that uses Gemini models to generate images.
• Groq Audio Tools: Added a tool that uses Groq models to translate, transcribe and generate audio.

Improvements:

• PubmedTools Expanded Results: Added expanded result sets for PubmedTools .
• Variety in Tool Results: Custom tools can now have any return type and it would be handled before being provided to the model.

Bug Fixes:

• Teams Shared Model Bug: Fixed issues where a single model is used across team members. This should reduce tool call failures in team execution.

What's Changed

• agent-default-param-update-ag-3011 by @ysolanky in #2954
• Added Read Timeout for MCP Client Session by @ssenthilnathan3 in #2961
• Add cartesia tool by @manthanguptaa in #2412
• Feat/mcp-sse: Extending MCP with SSE transport by @dsaad68 in #2892
• pyproject-keywords-ag-3013 by @ysolanky in #2957
• Fix cases where streaming breaks print_response by @dirkbrnd in #2964
• Feature: Implement shared team session state by @dirkbrnd in #2956
• Add execution hooks for agents and teams by @dirkbrnd in #2920
• Make sure model tools are unique when model is shared in team by @dirkbrnd in #2947
• Gemini image tool by @Mustafa-Esoofally in #2952
• fix-function-result-type-ag-3014 by @ysolanky in #2974
• Groq native model tools by @Mustafa-Esoofally in #2970
• Release 1.4.2 by @dirkbrnd in #2965

New Contributors

• @ssenthilnathan3 made their first contribution in #2961
• @dsaad68 made their first contribution in #2892

Full Changelog: v1.4.1...v1.4.2

v1.4.1

What's Changed

• chore(playground): cookbook showing an agent with structured outputs in the playground by @manuhortet in #2942
• toolkit-fix-ag-3008 by @ysolanky in #2939
• Extracting website main content should return content as text if all else fails by @mkschreder in #2804
• added option to Send Meeting notification to attendees by @aakashsengar in #2656
• Enhanced PubmedTools with More Comprehensive Article Data by @gusmmm in #2457
• Fix: memory hydration by @ashpreetbedi in #2950
• v1.4.1 by @ashpreetbedi in #2951

New Contributors

• @mkschreder made their first contribution in #2804
• @gusmmm made their first contribution in #2457

Full Changelog: v1.4.0...v1.4.1

v1.4.0

Changelog

New Features:

• Memory Generally Available: We have made improvements and adjustments to how Agentic user memory management works. This is now out of beta and generally available. See these examples and these docs for more info.
• OpenAI Tools: Added OpenAITools to enable text-to-speech and image generation through OpenAI’s APIs.
• Zep Tools: Added ZepTools and AsyncZepTools to manage memories for your Agent using zep-cloud

Improvements:

• Azure AI Foundry Reasoning: Added support for reasoning models via Azure AI Foundry. E.g. Deepseek-R1.
• Include/Exclude Tools: Added include_tools and exclude_tools for all toolkits. This allows for selective enabling / disabling of tools inside toolkits, which is especially useful for larger toolkits.

Bug Fixes:

• Gemini with Memory: Fixed issue with deepcopy when Gemini is used with Memory.

Breaking Changes:

• Memory: Agents will now by default use an improved Memory instead of the now deprecated AgentMemory.
  • agent.memory.messages → run.messages for run in agent.memory.runs (or agent.get_messages_for_session())
  • create_user_memories → enable_user_memories and is now set on the Agent/Team directly.
  • create_session_summary → enable_session_summaries and is now set on the Agent/Team directly.

What's Changed

• improve instruction for agno assist by @anuragts in #2917
• Add azure AI foundry for reasoning by @dirkbrnd in #2923
• fix: fixed auto-escaping issue in debug mode when content is in Chine… by @KinonoChen in #2915
• zep-integration-ag-2991 by @ysolanky in #2853
• Openai native model tool calls by @Mustafa-Esoofally in #2736
• Feature: Include/Exclude tools from toolkit by @dirkbrnd in #2918
• agent.py fix by @ashpreetbedi in #2936
• update-stale-issues-workflow-ag-3007 by @ysolanky in #2935
• fix(mcp): handle empty exclude_tools field by @manuhortet in #2941
• fix(playground): stream response only if response is streamable by @manuhortet in #2930
• Fix gemini deepcopy by @dirkbrnd in #2922
• fix/remove memory from agentic rag by @Ayush0054 in #2890
• Release 1.4.0 by @dirkbrnd in #2932

New Contributors

• @KinonoChen made their first contribution in #2915

Full Changelog: v1.3.5...v1.4.0

v1.3.5

Changelog

Improvements:

• Further Async Vector DB Support: Support added for:
  • Clickhouse
  • ChromaDB
  • Cassandra
  • PineconeDB
  • Pgvector
• Reasoning on Agno Platform:
  • Added extensive support for reasoning on the Agno Platform. Go see your favourite reasoning agents in action!
  • Changes from SDK
    • Now sending events for the different types of reasoning and populate the reasoning_content on RunResponse for stream/non-stream, async/non-async
    • Unified json structure for all types of reasoning in Reasoning events
• Google Caching Support: Added support for caching files and sending the cached content to Gemini.

Bug Fixes

• Firecrawl Scrape: Fixed issues with non-serializable types for during Firecrawl execution. #2883

What's Changed

• Demo Agents by @ashpreetbedi in #2906
• Fix accuracy eval by @dirkbrnd in #2913
• add clickhouse async support by @kausmeows in #2905
• Feature/reasoning by @kausmeows in #2760
• add chromadb async support by @kausmeows in #2904
• Check data existence in doc_id before inserting by @alpha-xone in #2685
• add cassandra vector db async support by @kausmeows in #2903
• Async pinecone by @kausmeows in #2902
• Add example for caching with google by @dirkbrnd in #2893
• add pgvector async by @kausmeows in #2901
• fix: firecrawl scrape api by @kausmeows in #2888
• Release 1.3.5 by @dirkbrnd in #2914

New Contributors

• @alpha-xone made their first contribution in #2685

Full Changelog: v1.3.4...v1.3.5

v1.3.4

What's Changed

• insert/upsert/log_info only if there are documents from reader by @5739n4 in #2869
• fix deepseek api key validation by @arnnv in #2856
• Ollama temperature example cookbook by @willemcdejongh in #2835
• fix: DynamoDBStorage #2797 by @jlonge4 in #2798
• update: AzureOpenAIEmbedder to consider client params passed in client_params arg by @skiran252 in #2764
• Add mode attribute to team data serialization in Team class by @Ayush0054 in #2725
• chore: add "exports" to init files that only import by @dbluhm in #2766
• Examples for session state by @ashpreetbedi in #2872
• Added webbrowser tool by @VirusDumb in #2634
• Reasoning multi purpose example by @dirkbrnd in #2808
• feat(URL): add proxy parameter by @KageyamaJie in #2876
• feat(PDF): add proxy parameter by @KageyamaJie in #2877
• Use built in LiteLLM functionality to validate the environment by @njbrake in #2852
• Memory Updates for better memory management by @dirkbrnd in #2873
• Give db session state preference by @ashpreetbedi in #2884
• v1.3.4 by @ashpreetbedi in #2885

New Contributors

• @5739n4 made their first contribution in #2869
• @arnnv made their first contribution in #2856
• @jlonge4 made their first contribution in #2798
• @skiran252 made their first contribution in #2764
• @dbluhm made their first contribution in #2766
• @VirusDumb made their first contribution in #2634
• @KageyamaJie made their first contribution in #2876
• @njbrake made their first contribution in #2852

Full Changelog: v1.3.3...v1.3.4

v1.3.3

Changelog

Improvements:

• Gemini File Upload: Enabled direct use of uploaded files with Gemini.
• Metrics Update: Added audio, reasoning and cached token counts to metrics where available on models.
• Reasoning Updates: We now natively support Ollama and AzureOpenAI reasoning models.

Bug Fixes:

• PPrint Util Async: Added apprint_run_response to support async.
• Mistral Reasoning: Fixed issues with using a Mistral model for chain-of-thought reasoning.

What's Changed

• Updates for 1.3.3 by @ashpreetbedi in #2858
• Gemini 2.5 learning assistant by @Mustafa-Esoofally in #2568
• feat: add audio, cached and reasoning tokens to the metrics by @manuhortet in #2863
• gemini-file-update-ag-2994 by @ysolanky in #2867
• add mistral reasoning True fix by @kausmeows in #2843
• update-history-params-ag-2995 by @ysolanky in #2868
• Reasoning Updates Ollama / AzureOpenAI by @dirkbrnd in #2862
• Release 1.3.3 by @dirkbrnd in #2866

Full Changelog: v.1.3.2...v1.3.3

v1.3.2

Changelog

New Features:

• Redis Memory DB: Added Redis as a storage provider for Memory. See here.

Improvements:

• Memory Updates: Various performance improvements made and convenience functions added:
  • agent.get_session_summary() → Use to get the previous session summary from the agent.
  • agent.get_user_memories() → Use to get the current user’s memories.
  • You can also add additional instructions to the MemoryManager or SessionSummarizer.
• Confluence Bypass SSL Verification: If required, you can now skip SSL verification for Confluence connections.
• More Flexibility On Team Prompts: Added add_member_tools_to_system_message to remove the member tool names from the system message given to the team leader, which allows flexibility to make teams transfer functions work in more cases.

Bug Fixes:

• LiteLLM Streaming Tool Calls: Fixed issues with tool call streaming in LiteLLM.
• E2B Casing Issue: Fixed issues with parsed Python code that would make some values lowercase.
• Team Member IDs: Fixed edge-cases with team member IDs causing teams to break.

What's Changed

• litellm toolcall+stream break fix by @kausmeows in #2765
• Add a demo team workflow by @mishramonalisha76 in #2779
• Add example of custom tool with session state by @dirkbrnd in #2815
• add redis to memory v2 by @kausmeows in #2831
• Memory performance updates by @dirkbrnd in #2814
• Confluence bypass ssl by @dirkbrnd in #2840
• fix-perf-evals-ag-2985 by @ysolanky in #2841
• feat: log a warning msg when receiving input of unsupported type by @manuhortet in #2842
• fix true and false lowercase issue by @Ayush0054 in #2823
• Release 1.3.2 by @dirkbrnd in #2851

New Contributors

• @manuhortet made their first contribution in #2842

Full Changelog: v1.3.1...v.1.3.2

v1.3.1

What's Changed

• Update reasoning cookbooks link by @ravi03071991 in #2807
• v1.3.1 by @ashpreetbedi in #2811

New Contributors

• @ravi03071991 made their first contribution in #2807

Full Changelog: v1.3.0...v1.3.1

v1.3.0

Changelog

New Features:

• Memory Revamp (beta): Releasing a complete revamp of Agno Memory (beta release). This includes a new Memory class that supports adding, updating and deleting user memories, as well as doing semantic search with a model. This also adds additional abilities to the agent to manage memories on your behalf. See the docs here.
• User ID and Session ID on Run: You can now pass user_id and session_id on agent.run(). This will ensure the agent is set up for the session belonging to the session_id and that only the memories of the current user is accessible to the agent. This allows you to build multi-user and multi-session applications with a single agent configuration.
• Redis Storage: Support added for Redis as a session storage provider.

What's Changed

• Memory 2.0 by @dirkbrnd in #2631
• update-pr-template-ag-2973 by @ysolanky in #2785
• add redis storage class by @kausmeows in #2794
• Release 1.3.0 by @dirkbrnd in #2796

Full Changelog: v1.2.16...v1.3.0

v1.2.16

Changelog

Improvements:

• Teams Improvements: Multiple improvements to teams to make task forwarding to member agents more reliable and to make the team leader more conversational. Also added various examples of reasoning with teams.
• Knowledge on Teams: Added knowledge to Team to better align with the functionality on Agent. This comes with retriever to set a custom retriever and search_knowledge to enable Agentic RAG.

Bug Fixes:

• Gemini Grounding Chunks: Fixed error when Gemini Grounding was used in streaming.
• OpenAI Defaults in Structured Outputs: OpenAI does not allow defaults in structured outputs. To make our structured outputs as compatible as possible without adverse effects, we made updates to OpenAIResponses and OpenAIChat.

What's Changed

• structured-outputs-fix-ag-2966 by @ysolanky in #2751
• Add default IDs for agent/team/workflow in playground apps by @dirkbrnd in #2748
• Fix(gemini): Prevent TypeError when parsing null grounding_chunks by @JoAz111 in #2687
• Fix task forwarding issues in Teams by @dirkbrnd in #2757
• add index name in Mongodb by @pritipsingh in #2773
• Release 1.2.16 by @dirkbrnd in #2775

New Contributors

• @JoAz111 made their first contribution in #2687

Full Changelog: v1.2.15...v1.2.16