NewYour coding agent can read the release notes before it upgrades.Set up the MCP server →
PyPI, #2885 most downloaded on PyPI
The programming language for agentic software.
Latest stable
3.2.0
Last release 9 days ago
12 Nov 2026
Ships on a steady schedule
a new release about every 9 days
Nearly every release is documented
notes for 59 of the last 60 stable releases
Nothing withdrawn
no release was ever pulled
2 years old
278 releases · first in 2024
Drag across the ruler to compare, or tap a release to open it.
GPT-5 Compatibility: Support for GPT-5 with our OpenAIResponses class
OpenAIResponses classPDFKnowledgeBase.role parameter to the Team class for defining the team's purpose and specialization.OpenAIResponses classFull Changelog: https://github.com/agno-agi/agno/compare/v1.7.9...v1.7.10
Your coding agent can read these notes before it upgrades. Set up the MCP server →
Reranker in Hybrid Search: Added support for Reranker in Pgvector hybrid search
stream_intermediate_steps with output modelmessage and messages.Full Changelog: https://github.com/agno-agi/agno/compare/v1.7.8...v1.7.9
Output model: Added support for output_model on Agents and Teams to generate the final response from output_model instead of model
output_model on Agents and Teams to generate the final response from output_model instead of modelservice_tier to OpenAIChat and OpenAIResponses.show_member_responses not working correctly on TeamYouTubeTranscriptApi has no attribute get_transcript :
YoutubeTranscriptApi is updated and now uses .fetch(video_id) for getting transcripts.tools_requiring_confirmation, tools_requiring_user_input, tools_awaiting_external_execution on the class BaseAgentRunResponseEventrun_id and a list of updated_tools to the continue_run or acontinue_run method.Full Changelog: https://github.com/agno-agi/agno/compare/v1.7.7...v1.7.8
[fix] Fix script injection vulnerability. by @kevinpetschik in https://github.com/agno-agi/agno/pull/3974
MCPTools and MultiMCPTools classes can now be initialized and used without an async context manager, providing a much easier experience. See the updated docs.Claude.LiteLLM.ZepTools are now compatible with Zep v3.dimensions length for text-embedding-3-small as 1536 and text-embedding-3-large as 3072.agno[arxiv] option for arxiv tool by @basnijholt in https://github.com/agno-agi/agno/pull/4036Full Changelog: https://github.com/agno-agi/agno/compare/v1.7.6...v1.7.7
feat: log warning if using deprecated sse transport with mcp by @manuhortet in https://github.com/agno-agi/agno/pull/3917
BitbucketTools with a variety of Bitbucket repository actions.JinaEmbedder for using embedding models via Jina.RowChunking as a CSV chunking strategy.EvmTools to do transactions on EVM compatible blockchains using web3.LinkupTools for powerful search.PostgresTools toolkit.Daytona agent Toolkitarun functions are treated. It now correctly keeps async generators as async generators and doesn’t convert it to a coroutine.
arun functions were incorrectly awaited as coroutines, which could cause runtime errors or prevent proper iteration through the yielded asynchronous values.async for. This ensures all yielded results are processed as intended within asynchronous workflows.tool_calls lost their individual argument streams. This has been resolved.Full Changelog: https://github.com/agno-agi/agno/compare/v1.7.5...v1.7.6
SurrealDB: Added SurrealDB support as a vector DB for knowledge bases.
cache_session attribute to allow users to switch off session caching, which improves on memory management.FastAPIApp .Full Changelog: https://github.com/agno-agi/agno/compare/v1.7.4...v1.7.5
Workflows Revamped (beta): Our new Workflows implementation (internally referred to as Workflows 2.0) is a complete redesign of the workflow system in
<img width="868" height="237" alt="image" src="https://github.com/user-attachments/assets/489499a1-f301-4139-9273-a275f5a142a7" />
Full Changelog: https://github.com/agno-agi/agno/compare/v1.7.3...v1.7.4
Session State on Run: You can now pass session_state when running an agent or team. See docs for more information.
session_state when running an agent or team. See docs for more information.GCSPDFKnowledgeBase to support PDFs on Google Cloud Storage.DocumentKnowledgeBaseAgent where history is enabled.format.bat, enable the .venv environment when available. by @Siete-F in https://github.com/agno-agi/agno/pull/3807Full Changelog: https://github.com/agno-agi/agno/compare/v1.7.2...v1.7.3
MySQL Storage: Added support for MySQLStorage as an agent/team/workflow session storage backend.
MySQLStorage as an agent/team/workflow session storage backend.o4-mini-deep-research and o3-deep-research models.memory_growth_tracking as an attribute on PerformanceEval to enable additional debug logs for memory growth.agent and team as optional parameters in tool hooks, for more flexibility.Full Changelog: https://github.com/agno-agi/agno/compare/v1.7.1...v1.7.2
Debug Level: Added debug_level to both Agent and Team. This is an int value of either 1 (default) or 2 (more verbose logging). Currently this only ena
debug_level to both Agent and Team. This is an int value of either 1 (default) or 2 (more verbose logging). Currently this only enables more verbose model logs, but will be used more widely in future.parser_model support for Team. See docs here.thinking_budget and include_thoughts parameters for Gemini model class.search_news , search_scholar and scrape_webpage.OxylabsTools for adding more web-scraping capabilities to agents.read_csv method for improved CSV parsingfull_team_session_metrics on Teams.Full Changelog: https://github.com/agno-agi/agno/compare/v1.7.0...v1.7.1
Agent/Team Add Tool: Added convenience function to Agent and Team → add_tool(tool) to append new tools after inititialisation.
Agent and Team → add_tool(tool) to append new tools after inititialisation.response_model is passed. The structured output itself is not streamed, but it is part of the iterator response when running an agent/team with streaming. The response model is set on a single RunResponseContentEvent and on the final RunResponseCompletedEvent.run(..., stream=True) or arun(..., stream=True) on Agent or Team with a response_model set, the current behaviour would switch off streaming and respond with a single RunResponse object. After the changes mentioned above, you will get the Iterator[RunResponseEvent] / AsyncIterator[RunResponseEvent] response instead.Full Changelog: https://github.com/agno-agi/agno/compare/v1.6.4...v1.7.0
Brightdata Toolkit: Added multiple web-based tools via Brightdata.
search to FileTools.upsert not using the parameter filtersteam.rename_session(...) that raises an AttributeErrorSerperApiTools: Refactored SerperApiTools to SerperTools for clearer naming.Full Changelog: https://github.com/agno-agi/agno/compare/v1.6.3...v1.6.4
User Control Flows on Playground: The Agno Platform now support user control flows on the playground.
store_events parameter to optionally add all events that happened during the course of an agent/team run on the RunResponse/TeamRunResponse.csv and csv_url knowledge bases: Add knowledge filters support for these knowledge base types.a prefix from async function names: asearch_knowledge_base, etc will now be the same as their sync counterparts when sent to the model. The names of functions are important for accurate function calling.agent_id not set.ObjectId is not JSON serializableFull Changelog: https://github.com/agno-agi/agno/compare/v1.6.2...v1.6.3
chore: Release 1.6.2 by @dirkbrnd in https://github.com/agno-agi/agno/pull/3559
Full Changelog: https://github.com/agno-agi/agno/compare/v1.6.1...v1.6.2
Nebius Embeddings: Added support for embedding models on Nebius.
agent_name to agent events, and team_name to team events. Also added team_session_id to team-member events to indicate that it belongs to the top-level team session.stream_member_events to teams to optionally disable streaming of member events.async support on DocumentKnowledgeBaseenum parameters in custom tools.Full Changelog: https://github.com/agno-agi/agno/compare/v1.6.0...v1.6.1
New Streaming Events: We have improved our streaming events system. See the details in “breaking changes” section at the bottom.
RunResponse now does not have an event attribute. It still represents the responses of the entire run.RunResponse.status now indicates whether the run response is RUNNING, PAUSED, or CANCELLED.agent.run(..., stream=True) or agent.arun(..., stream=True) .RunResponseContentRunErrorRunCancelledToolCallStartedToolCallCompletedstream_intermediate_steps=True:
RunStartedRunCompletedReasoningStartedReasoningStepReasoningCompletedMemoryUpdateStartedMemoryUpdateCompletedTeamRunResponseContentTeamRunErrorTeamRunCancelledTeamToolCallStartedTeamToolCallCompletedstream_intermediate_steps=True:
TeamRunStartedTeamRunCompletedTeamReasoningStartedTeamReasoningStepTeamReasoningCompletedTeamMemoryUpdateStartedTeamMemoryUpdateCompletedWorkflowRunResponseStartedEvent and WorkflowRunResponseCompletedEvent events.Full Changelog: https://github.com/agno-agi/agno/compare/v1.5.10...v1.6.0
Playground File Upload: We now support file upload via the Agno Playground. This will send PDF, CSV, Docx, etc files directly to the agents/teams for
research tool on ExaTools. See more on their docs about how their research works.Full Changelog: https://github.com/agno-agi/agno/compare/v1.5.9...v1.5.10
ZepTools Updates: Updated ZepTools to remove deprecated features.
SerperTools toolkit to search GooglePDFBytesKnowledgeBase, which allows the ingestion of in-memory PDF content via bytes or IO streams instead of file paths.DaytonaTools toolkit to let Agents execute code remotely on Daytona sandboxesAWSSESTools to send emails via AWS SES.add_location_to_instructions to automatically detect the current location where the agent is running and add that to the system message.agent was replaced with agents, team with teams and workflows was added. This also now requires you to specify which agent/team/workflow to run.
http://localhost:8001/runs?agent_id=my-agentZepTools to remove deprecated features.GmailTools now support attachments.fetch_with_retry and async_fetc_with_retry to be reused inurl_reader.pysearch_posts for XTools.slack, whatsapp, etcRunResponse.to_dict() to handle non-serializable fields, as Python enumsFull Changelog: https://github.com/agno-agi/agno/compare/v1.5.8...v1.5.9
Slack App: Introducing the SlackApp to allow you to create agents for Slack! The app allows agents to respond to individual messages or on group chats
SlackApp to allow you to create agents for Slack! The app allows agents to respond to individual messages or on group chats, and it creates threads to respond to messages.VisualizationTools that uses matplotlib to give agents the ability to make graphs.BraveSearch that allows agent to search the web using brave search api.knowledge_filters even if self.add_references=True which is a case for traditional RAG (diff from Agentic RAG)Mem0ToolsSearxng tool initialization: Fixed Searxng tool initialization error
AttributeError: 'Searxng' object has no attribute 'include_tools'
and added comprehensive unit tests.
Fix for enum as a response model for Gemini: With 1.5.6, a bug was introduced now allowing enum as a data type for Gemini response model.
OpenAI parsing structured output: With the changes in the OpenAI library we don't need to parse the structured output separately.
Fix accuracy evals monitoring: Added logic to handle monitoring when evaluating Teams in the run function of AccuracyEval
FastAPIApp does not have a default prefix anymore and /run → /runs (i.e. the created run endpoint is now <your_domain>/runs)serve_fastapi_app is now replaced with .serve() on the instance of FastAPIApp.serve_whatsapp_app is now replaced with .serve() on the instance of WhatsappAPI.Team Evals: Evaluations are now supported for teams!
arun support for Workflows, so they can now be used with async Python.tool_call_limit: Revamp of tool_call_limit to make it work across a whole agent run.run.team_session_state is now correctly propagated and shared between all members and sub-teams of a team.Dict[str, int] fields (and other Dict types) were failing when used as response_schema for both OpenAI and Gemini models due to schema format incompatibilities.session_name is now available after a run.team_session_state, you now have to set team_session_state on the Team instead of session_state.Full Changelog: https://github.com/agno-agi/agno/compare/v1.5.5...v1.5.6
chore: update qdrant to remove hybrid search breaking change by @kausmeows in https://github.com/agno-agi/agno/pull/3360
AI/ML API, a platform providing AI/ML models. AI/ML API provides 300+ AI models including Deepseek, Gemini, ChatGPT. The models run at enterprise-grade rate limits and uptimes.Pydantic and dataclass objects as input to a function. See here for an example.concurrent.futures module to enforce timeouts on all Exa API operations (search, get contents, find similar, and answer generation).get_previous_session_messages(number_of_sessions: int) that returns a list of messages that the agent can analysesearch_previous_sessions_historyexpire key to set TTL on Redis keys.cache_creation_input_tokens to agent session metrics, to allow for tracking Anthropic cache write statistics.post on their InferenceClient()- https://discuss.huggingface.co/t/getting-error-attributeerror-inferenceclient-object-has-no-attribute-post/156682id: str = "jinaai/jina-embeddings-v2-base-code" as default, because these models are no longer provided by the HF Inference API. Changed the default to id: str = "intfloat/multilingual-e5-large"role_map for OpenAIChat: This allows certain models that don’t adhere to OpenAI’s role mapping to be used vir OpenAILike.content_hash in upsert as ID.Full Changelog: https://github.com/agno-agi/agno/compare/v1.5.4...v1.5.5
User Control Flows: This is the beta release of Agno’s Human-in-the-loop flows and tools.
paused awaiting completion of certain user requirements before the agent can continue.agent.continue_run and agent.acontinue_run functions.@tool(requires_confirmation=True) and the agent will expect user confirmation before executing the tool.@tool(requires_user_input=True) to have the agent stop and ask for user input before continuing.@tool(external_execution=True) to indicate that you will execute this function outside of the agent context.UserControlFlowTools() to an agent to give the agent the ability to dynamically stop the flow and ask for user input where required.FirecrawlTools.include_tools and exclude_tools.Full Changelog: https://github.com/agno-agi/agno/compare/v1.5.3...v1.5.4
Improved Accuracy Evals: Updated the way accuracy evals works for more accurate agent-based evaluation.
Full Changelog: https://github.com/agno-agi/agno/compare/v1.5.2...v1.5.3
Agno Apps (Beta): Introducing Agno Apps, convenience functions to assist with building production-ready applications. The first supported apps are:
FastAPIApp → A really simple FastAPI server that provides access to your agent or team.WhatsappAPIApp → An app that implements the Whatsapp protocol allowing you to have an Agno agent running on Whatsapp. Supports image / audio / video input and can generate images as responses. Supports reasoning.cosmos_compatibility=Truepdf and text s3 readers.stop_after_tool_call and show_result for Toolkits: Now the base Toolkit class has stop_after_tool_call_tools and show_result_tools similar to the @tool decorator.WebsiteReader._extract_main_content by 72% by @misrasaurabh1 in https://github.com/agno-agi/agno/pull/3013Full Changelog: https://github.com/agno-agi/agno/compare/v1.5.1...v1.5.2
Nebius Model Provider: Added Nebius as a model provider.
ssl parameter to Redis storage.Full Changelog: https://github.com/agno-agi/agno/compare/v.1.5.0...v1.5.1
Azure OpenAI Tools: Added image generation via Dall-E via Azure AI Foundry.
hybrid_search on Milvus.PerfEval to PerformanceEvalagent, prompt and expected_answerstream=True). Individual events will have more relevant data now.Full Changelog: https://github.com/agno-agi/agno/compare/v1.4.6...v1.5.0
Azure OpenAI Tools: Added image generation via Dall-E via Azure AI Foundry.
hybrid_search on Milvus.PerfEval to PerformanceEvalagent, prompt and expected_answerstream=True). Individual events will have more relevant data now.Full Changelog: https://github.com/agno-agi/agno/compare/v1.4.6...v1.5.0
Cerebras Model Provider: Added Cerebras as a model provider.
Two Ways to Apply Filters:
Explicit Filtering: Pass filters directly to Agent or during run/query
# Option 1: Filters on Agent initialization
agent = Agent(
knowledge=knowledge_base,
knowledge_filters={"filter_1": "abc"}
)
# Option 2: Filters on run execution
agent.run("Tell me about...", knowledge_filters={"filter_1": "abc"})
See docs here
Agentic Filtering: Agent automatically detects and applies filters from user queries
# Enable automatic filter detection
agent = Agent(
knowledge=knowledge_base,
enable_agentic_knowledge_filters=True
)
# Agent extracts filters from query
agent.run("Tell me about John Doe's experience...")
See docs here
Two approaches for adding metadata to documents:
During Knowledge Base Initialization:
knowledge_base = PDFKnowledgeBase(path=[
{
"path": "file_1.pdf",
"metadata": {
"user_id": "abc"
}
},
{
"path": "file_2.pdf",
"metadata": {
"user_id": "xyz"
}
}
])
During Individual Document Loading:
knowledge_base.load_document(
path="file.pdf",
metadata={"user_id": "abc"}
)
Compatibility
PDF, Text, DOCX, JSON, and PDF_URLQdrant, LanceDB, and MongoDBcurrent_user_id and current_session_id as default variables in session_data.abc.-.xyz.pdf and abc.-.def.pdf) were being incorrectly identified due to the readers using formatted names as unique id which were getting uniqueness conflict. Introduced a unique ID for each document in all the readers using uuidv4() to ensure strict identification and prevent conflicts.Full Changelog: https://github.com/agno-agi/agno/compare/v1.4.5...v1.4.6
Embedder Support via AWS Bedrock: AwsBedrockEmbedder has been added with a default embedding model of cohere.embed-multilingual-v3.
AwsBedrockEmbedder has been added with a default embedding model of cohere.embed-multilingual-v3.GeminiTools.ApifyTools to make it completely compatible with Apify actors.Full Changelog: https://github.com/agno-agi/agno/compare/v1.4.4...v1.4.5
OpenAI File Support: Added support for File attached to prompts for agents with OpenAIChat models.
File attached to prompts for agents with OpenAIChat models.retriever parameter can now be an async function to be used with agent.arun and agent.aprint_response.Video(url=...) for Gemini.OpenAIResponses.MCPTools usage while calling agent.acli_app.request_params to Bedrock Converse API by @leandrodamascena in https://github.com/agno-agi/agno/pull/3035Full Changelog: https://github.com/agno-agi/agno/compare/v1.4.3...v1.4.4
Llama API: Added native SDK and OpenAI-like model classes.
Full Changelog: https://github.com/agno-agi/agno/compare/v1.4.2...v1.4.3
MCP SSE Support: Added support for connecting to SSE MCP Servers.
Toolkits and custom tools. See this example.PubmedTools .Full Changelog: https://github.com/agno-agi/agno/compare/v1.4.1...v1.4.2
chore(playground): cookbook showing an agent with structured outputs in the playground by @manuhortet in https://github.com/agno-agi/agno/pull/2942
Full Changelog: https://github.com/agno-agi/agno/compare/v1.4.0...v1.4.1
Memory: Agents will now by default use an improved Memory instead of the now deprecated AgentMemory.
OpenAITools to enable text-to-speech and image generation through OpenAI’s APIs.ZepTools and AsyncZepTools to manage memories for your Agent using zep-cloudinclude_tools and exclude_tools for all toolkits. This allows for selective enabling / disabling of tools inside toolkits, which is especially useful for larger toolkits.deepcopy when Gemini is used with Memory.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.Full Changelog: https://github.com/agno-agi/agno/compare/v1.3.5...v1.4.0
Further Async Vector DB Support: Support added for:
reasoning_content on RunResponse for stream/non-stream, async/non-asyncReasoning eventsdoc_id before inserting by @alpha-xone in https://github.com/agno-agi/agno/pull/2685Full Changelog: https://github.com/agno-agi/agno/compare/v1.3.4...v1.3.5
insert/upsert/log_info only if there are documents from reader by @5739n4 in https://github.com/agno-agi/agno/pull/2869
client_params arg by @skiran252 in https://github.com/agno-agi/agno/pull/2764Full Changelog: https://github.com/agno-agi/agno/compare/v1.3.3...v1.3.4
Gemini File Upload: Enabled direct use of uploaded files with Gemini.
apprint_run_response to support async.Full Changelog: https://github.com/agno-agi/agno/compare/v.1.3.2...v1.3.3
Redis Memory DB: Added Redis as a storage provider for Memory. See here.
Memory. See here.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.MemoryManager or SessionSummarizer.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.Full Changelog: https://github.com/agno-agi/agno/compare/v1.3.1...v.1.3.2
Update reasoning cookbooks link by @ravi03071991 in https://github.com/agno-agi/agno/pull/2807
Full Changelog: https://github.com/agno-agi/agno/compare/v1.3.0...v1.3.1
Memory Revamp (beta): Releasing a complete revamp of Agno Memory (beta release). This includes a new Memory class that supports adding, updating and d
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 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.Full Changelog: https://github.com/agno-agi/agno/compare/v1.2.16...v1.3.0
Teams Improvements: Multiple improvements to teams to make task forwarding to member agents more reliable and to make the team leader more conversatio
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.OpenAIResponses and OpenAIChat.Full Changelog: https://github.com/agno-agi/agno/compare/v1.2.15...v1.2.16
Update: SQL Agent by @ashpreetbedi in https://github.com/agno-agi/agno/pull/2734
Full Changelog: https://github.com/agno-agi/agno/compare/v1.2.14...v1.2.15
Improved Github Tools: Added many more capabilities to GithubTools.
GithubTools.Full Changelog: https://github.com/agno-agi/agno/compare/v1.2.13...v1.2.14
v1.2.13 by @ashpreetbedi in https://github.com/agno-agi/agno/pull/2719
Full Changelog: https://github.com/agno-agi/agno/compare/v1.2.12...v1.2.13
Timezone Identifier: Added a new timezone_identifier parameter in the Agent class to include the timezone alongside the current date in the instructio
timezone_identifier parameter in the Agent class to include the timezone alongside the current date in the instructions.ReasoningTools for an advanced reasoning scratchpad for agents.async-await support:
Full Changelog: https://github.com/agno-agi/agno/compare/v1.2.11...v1.2.12
Fix for structured outputs: Fixed cases of structured outputs for reasoning.
Full Changelog: https://github.com/agno-agi/agno/compare/v1.2.10...v1.2.11
Knowledge Tools: Added KnowledgeTools for thinking, searching and analysing documents in a knowledge base.
KnowledgeTools for thinking, searching and analysing documents in a knowledge base.Full Changelog: https://github.com/agno-agi/agno/compare/v1.2.9...v1.2.10
Simpler MCP Interface: Added MultiMCPTools to support multiple server connections and simplified the interface to only allow command to be passed. See
MultiMCPTools to support multiple server connections and simplified the interface to only allow command to be passed. See these examples of how to use it. See the updated docs.Full Changelog: https://github.com/agno-agi/agno/compare/v1.2.8...v1.2.9
Toolkit Instructions: Extended Toolkit with instructions and add_instructions to enable you to specify additional instructions related to how a tool s
Toolkit with instructions and add_instructions to enable you to specify additional instructions related to how a tool should be used. These instructions are then added to the model’s “system message” if add_instructions=True .Full Changelog: https://github.com/agno-agi/agno/compare/v1.2.7...v1.2.8
Created: March 31, 2025 4:13 PM
Created: March 31, 2025 4:13 PM
gemini-2.0-flash-exp-image-generation model.@tool decorator. See the docs here.async-await support, so it will be used in agent.arun and agent.aprint_response. This also means that knowledge_base.aload() is possible which should greatly increase loading speed in some cases. The following have been converted:
JSONKnowledgeBase → Here is a cookbook to illustrate how to use it.PDFKnowledgeBase → Here is a cookbook to illustrate how to use it.PDFUrlKnowledgeBase → Here is a cookbook to illustrate how to use it.CSVKnowledgeBase → Here is a cookbook to illustrate how to use it.CSVUrlKnowledgeBase → Here is a cookbook to illustrate how to use it.ArxivKnowledgeBase → Here is a cookbook to illustrate how to use it.WebsiteKnowledgeBase → Here is a cookbook to illustrate how to use it.YoutubeKnowledgeBase → Here is a cookbook to illustrate how to use it.TextKnowledgeBase → Here is a cookbook to illustrate how to use it.Full Changelog: https://github.com/agno-agi/agno/compare/v1.2.6...v1.2.7
Gemini Function call result fix: Fixed a bug with function call results failing formatting and added proper role mapping
Full Changelog: https://github.com/agno-agi/agno/compare/v1.2.5...v1.2.6
E2B Tools: Added E2B Tools to run code in E2B Sandbox
tools and tool_call_limit to Team. This means the team leader itself can also have tools provided by the user, so it can act as an agent.MCPTools to allow you to specify tools to specifically include or exclude from all the available tools on an MCP server. This is very useful for limiting which tools the model has access to.@tool() decorator now supports async functions, including async pre and post-hooks.tool_choice from Ollama usage as it is not supported.entity_id mappingsFull Changelog: https://github.com/agno-agi/agno/compare/v1.2.4...v1.2.5
Tool Choice on Teams: Made tool_choice configurable.
tool_choice configurable.update_task on TodoistTools.Full Changelog: https://github.com/agno-agi/agno/compare/v1.2.3...v1.2.4
Teams Error Handling: Improved the flow in cases where the model gets it wrong when forwarding tasks to members.
Full Changelog: https://github.com/agno-agi/agno/compare/v1.2.2...v1.2.3
Teams Memory: Fixed issues related to memory not persisting correctly across multiple sessions.
Full Changelog: https://github.com/agno-agi/agno/compare/v1.2.1...v1.2.2
Teams Markdown: Fixed issue with markdown in teams responses.
Full Changelog: https://github.com/agno-agi/agno/compare/v1.2.0...v1.2.1
Add fallback to deprecated imghdr by @Sebastiao-Assuncao in https://github.com/agno-agi/agno/pull/2487
MCPTools for connections to external MCP servers. See the updated docs.Full Changelog: https://github.com/agno-agi/agno/compare/v1.1.17...v1.2.0
Better Debug Logs: Enhanced debug logs for better readability and clarity.
Full Changelog: https://github.com/agno-agi/agno/compare/v1.1.16...v1.1.17
Async Qdrant VectorDB: Implemented async support for Qdrant VectorDB, improving performance and efficiency.
Full Changelog: https://github.com/agno-agi/agno/compare/v1.1.15...v1.1.16
Function Result Caching: Added caching of selected searchers and scrapers. This is only intended for testing and should greatly improve iteration spee
print_response and aprint_response is used. They are now displayed in a separate panel different from response panel. It can also be used in conjunction in response_model.Full Changelog: https://github.com/agno-agi/agno/compare/v1.1.14...v1.1.15
One column per month.