Skip to content

Releases: agno-agi/agno

v1.6.0

10 Jun 19:15
@dirkbrnd dirkbrnd
v1.6.0
7772605
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.
Compare
Choose a tag to compare
v1.6.0

Changelog

Improvements:

  • New Streaming Events: We have improved our streaming events system. See the details in “breaking changes” section at the bottom.
  • Member Events in Teams: The above change includes streaming of events from team members with the top-level team events.

Bug Fixes:

  • Apify Tools: Fixed the ApifyTools initialize to correctly register functions.

Breaking Changes:

  • Updates to Run Without Streaming:
    • RunResponse now does not have an event attribute. It still represents the responses of the entire run.
    • An additional attribute RunResponse.status now indicates whether the run response is RUNNING, PAUSED, or CANCELLED.
  • Updates to Run Streaming:
    • In the case of streaming you now get reformulated run events. These events are streamed if you do agent.run(..., stream=True) or agent.arun(..., stream=True) .
    • Agents have the following event types:
      • RunResponseContent
      • RunError
      • RunCancelled
      • ToolCallStarted
      • ToolCallCompleted
      • with stream_intermediate_steps=True:
        • RunStarted
        • RunCompleted
        • ReasoningStarted
        • ReasoningStep
        • ReasoningCompleted
        • MemoryUpdateStarted
        • MemoryUpdateCompleted
    • See detailed documentation here.
  • Updates to Teams:
    • Teams have the following event types:
      • TeamRunResponseContent
      • TeamRunError
      • TeamRunCancelled
      • TeamToolCallStarted
      • TeamToolCallCompleted
      • with stream_intermediate_steps=True:
        • TeamRunStarted
        • TeamRunCompleted
        • TeamReasoningStarted
        • TeamReasoningStep
        • TeamReasoningCompleted
        • TeamMemoryUpdateStarted
        • TeamMemoryUpdateCompleted
    • Teams will also yield events from team members as they are executed.
    • See detailed documentation here.
  • Updates to Workflows:
    • You should now yield WorkflowRunResponseStartedEvent and WorkflowRunResponseCompletedEvent events.

What's Changed

Full Changelog: v1.5.10...v1.6.0

Contributors

dirkbrnd, pritipsingh, and Ayush0054
Loading

v1.5.10

07 Jun 04:29
@dirkbrnd dirkbrnd
v1.5.10
ecf03ba
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.
Compare
Choose a tag to compare
v1.5.10

Changelog

New Features:

  • 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 interpretation by the downstream LLMs. If you have a knowledge base attached to the agent/team, it will upload the file to the knowledge base instead.
  • Async Evals: Support for async and evaluations. See examples here.

Improvements:

  • Exa Research: Added research tool on ExaTools. See more on their docs about how their research works.
  • Whatsapp Type Indicator: Add type indicator to Whatsapp responses.

Bug Fixes:

  • State in Messages Fixes: Fixed issues around nested json inside messages and adding state into messages.
  • Anthropic Empty Responses: Fixed issue with Anthropic sometimes responding with empty message.

What's Changed

New Contributors

Full Changelog: v1.5.9...v1.5.10

Contributors

manuhortet, nebulaanish, and 4 other contributors
Loading

v1.5.9

05 Jun 19:40
@kausmeows kausmeows
v1.5.9
1a11436
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.
Compare
Choose a tag to compare
v1.5.9

Changelog

New Features:

  • AG-UI App: Expose your Agno Agents and Teams with an AG-UI compatible FastAPI APP.
  • vLLM Support: Added support for running vLLM models via Agno.
  • Serper Toolkit: Added SerperTools toolkit to search Google
  • LangDB Support: Added LangDB AI Gateway support into Agno.
  • LightRAG server support: Added LightRAG support which provides a fast, graph-based RAG system that enhances document retrieval and knowledge querying capabilities.
  • Parser Model: Added ability to use an external model to apply a structured output to a model response
  • Pdf Bytes Knowledge: Introduced a new knowledge base class: PDFBytesKnowledgeBase, which allows the ingestion of in-memory PDF content via bytes or IO streams instead of file paths.
  • Qdrant Mcp Server: Added MCP support for Qdrant
  • Daytona integration: Added DaytonaTools toolkit to let Agents execute code remotely on Daytona sandboxes
  • Expand URL addition in Crawl4ai: Introduced a new URL expansion feature directly into the Crawl4ai toolkit. Our agents frequently encounter shortened URLs that crawl4ai cannot scrape effectively, leading to incomplete data retrieval. With this update, shortened URLs are expanded to their final destinations before being processed by the crawler.
  • AWS SES Tools: Added AWSSESTools to send emails via AWS SES.
  • Location Aware Agents: Added add_location_to_instructions to automatically detect the current location where the agent is running and add that to the system message.

Improvements:

  • FastAPIApp Update: FastAPIApp was updated and 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.
    • E.g. http://localhost:8001/runs?agent_id=my-agent
  • ZepTools Updates: Updated ZepTools to remove deprecated features.
  • GmailTools Attachments: GmailTools now support attachments.
  • Improve code reusability by using fetch with retry and async_fetch_with_retry: updated fetch_with_retry and async_fetc_with_retry to be reused inurl_reader.py
  • Add name to evaluation examples: Included name param in evaluation examples
  • XTools Search: Added search_posts for XTools.

Bug Fixes:

  • Claude Prompt Tokens: Fixed a bug with prompt tokens not propagating in Claude model class
  • Add type in base App class for registry: Can have different types of app like- slack, whatsapp, etc
  • Accept empty array of pdf urls: Fixed an issue where empty PDF URL arrays were not accepted, preventing knowledge base queries without adding new documents
  • Anthropic cache metrics propagation: Fixed a bug where Anthropic's prompt caching metrics were not propagating to Agent responses, despite the raw Anthropic API working correctly. This minimal fix ensures cache performance metrics are properly captured and reported.
  • Handle non serializable objects on RunResponse dict parsing:
    • Updated RunResponse.to_dict() to handle non-serializable fields, as Python enums

What's Changed

New Contributors

Full Changelog: v1.5.8...v1.5.9

Contributors

bet0x, nikodyk, and 20 other contributors
Loading

v1.5.8

03 Jun 13:56
@kausmeows kausmeows
v1.5.8
d85ef65
Compare
Choose a tag to compare
v1.5.8

Changelog

New Features:

  • 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, and it creates threads to respond to messages.
  • Visualization Tools: Added VisualizationTools that uses matplotlib to give agents the ability to make graphs.
  • Brave Search Tools: Introduced a new toolkit for integrating BraveSearch that allows agent to search the web using brave search api.

Improvements:

  • Pass filters for traditional RAG: Properly pass down knowledge_filters even if self.add_references=True which is a case for traditional RAG (diff from Agentic RAG)
  • Add infer param to Mem0: Added infer as a param to Mem0Tools

Bug Fixes:

  • Searxng 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

Updates

  • Updates to Apps:
    • 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.
Loading

v1.5.6

29 May 18:49
@kausmeows kausmeows
v1.5.6
fadab82
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.
Compare
Choose a tag to compare
v1.5.6

Changelog

New Features

  • Team Evals: Evaluations are now supported for teams!

Improvements:

  • Async Workflows: Added arun support for Workflows, so they can now be used with async Python.
  • Parallel Memory Updates: Made speed improvements when user memories and session summaries are generated.
  • Reimplement tool_call_limit: Revamp of tool_call_limit to make it work across a whole agent run.

Bug Fixes:

  • Mistral Structured Outputs with Tools: Fixed an issue preventing Mistral model use with structured output and tools
  • Images In Run Without Prompt: Fixed issues related to images being ignored if there wasn’t a prompt provided on run.
  • Pgvector Upsert Fix: Fixed Pgvector upsert not copying metadata properly
  • Handle AgnoInstrumentor failing with OpenAIResponses: PR merged in Arize’s openinference repo- Arize-ai/openinference#1701
  • Pinecone Filters: Enabled filters for pinecone vector db
  • Combined KB Async: Add missing async method to Combined KB
  • Team Session State Fix: team_session_state is now correctly propagated and shared between all members and sub-teams of a team.
  • Gemini type fix for integers:
    • Pydantic models with 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: session_name is now available after a run.
  • Handle UUIDs while serialization in RedisStorage: Fixed error object of type UUID is not JSON serializable

Updates:

  • For managing team_session_state, you now have to set team_session_state on the Team instead of session_state.

What's Changed

Full Changelog: v1.5.5...v1.5.6

Contributors

manuhortet, willemcdejongh, and 4 other contributors
Loading

v1.5.5

27 May 10:29
@kausmeows kausmeows
v1.5.5
95bad1a
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.
Compare
Choose a tag to compare
v1.5.5

Changelog

New Features:

  • Claude File Upload: We can now upload a file to Anthropic directly and then use it as an input to an agent.
  • Claude 4 Code Execution Tool: Updated Claude to execute Python code in a secure, sandboxed environment.
  • Prompt caching with Anthropic Models: Allowed resuming from specific prefixes in your prompts. This approach significantly reduces processing time and costs for repetitive tasks or prompts with consistent elements.
  • Vercel v0 Model: Added support for new Vercel v0 models and cookbook examples.
  • Qdrant Hybrid Search support
  • Markdown Knowledge Base: Added native support for Markdown-based knowledge bases.
  • AI/ML API platform integration: Introduced integration with 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.
  • Update Pydantic and dataclass in function handling: Added support for Pydantic and dataclass objects as input to a function. See here for an example.

Improvements:

  • Timeout handling for API calls in ExaTools class:
    • Timeout functionality to Exa API calls to prevent indefinite hanging of search operations. The implementation uses Python's concurrent.futures module to enforce timeouts on all Exa API operations (search, get contents, find similar, and answer generation).
    • This change addresses the issue where Exa search functions would hang indefinitely, causing potential service disruptions and resource leaks.
  • Fetch messages from last N sessions:
    • A tool for the agent, something like get_previous_session_messages(number_of_sessions: int) that returns a list of messages that the agent can analyse
    • Switch on with search_previous_sessions_history
  • Redis Expiration: Added expire key to set TTL on Redis keys.
  • Add Anthropic Cache Write to Agent Session Metrics: Added cache_creation_input_tokens to agent session metrics, to allow for tracking Anthropic cache write statistics

Bug Fixes:

  • Huggingface Embedder Updates:
  • Add role_map for OpenAIChat: This allows certain models that don’t adhere to OpenAI’s role mapping to be used vir OpenAILike.
  • Use Content Hash as ID in Upsert in Pgvector: Use reproducible content_hash in upsert as ID.
  • Insert in Vector DB passes only last chunk meta_data: Insert in vector db passes only last chunk meta_data. issue link- https://discord.com/channels/965734768803192842/1219054452221153463/1376631140047130649
  • Remove Argument Sanitization: Replaced with a safer way to do this that won't break arguments that shouldn't be sanitized
  • Handle async tools when running async agents on playground: Fixed a regression where using Agents with async tools (e.g. MCP tools) was breaking in the Playground.

What's Changed

New Contributors

Full Changelog: v1.5.4...v1.5.5

Contributors

gsaada, manuhortet, and 12 other contributors
Loading

v1.5.4

23 May 15:37
@dirkbrnd dirkbrnd
v1.5.4
e886ecb
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.
Compare
Choose a tag to compare
v1.5.4

Changelog

New Features:

  • User Control Flows: This is the beta release of Agno’s Human-in-the-loop flows and tools.
    • We now allow agent runs to be paused awaiting completion of certain user requirements before the agent can continue.
    • This also adds the agent.continue_run and agent.acontinue_run functions.
    • The control flows that are available:
      • User confirmation flow → Decorate a function with @tool(requires_confirmation=True) and the agent will expect user confirmation before executing the tool.
      • User input required → Decorate a function with @tool(requires_user_input=True) to have the agent stop and ask for user input before continuing.
      • External tool execution → Decorate a function with @tool(external_execution=True) to indicate that you will execute this function outside of the agent context.
      • Dynamic user input → Add UserControlFlowTools() to an agent to give the agent the ability to dynamically stop the flow and ask for user input where required.
    • See a host of examples here.
    • We would appreciate any feedback from the community!
  • Mem0 Toolkit: Added a toolkit for managing memories in Mem0.
  • Firecrawl Search: Added support for Firecrawl web search in FirecrawlTools.

Bug Fixes:

  • Firecrawl Tools and Reader: Fixed parameter parsing for the Firecrawl reader and tools.
  • Include/Exclude on all Tools: Ensure all toolkits support include_tools and exclude_tools.

What's Changed

New Contributors

Full Changelog: v1.5.3...v1.5.4

Contributors

djoek, manuhortet, and 5 other contributors
Loading

v1.5.3

21 May 15:09
@dirkbrnd dirkbrnd
v1.5.3
8d1f410
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.
Compare
Choose a tag to compare
v1.5.3

Changelog

Improvements:

  • Improved Accuracy Evals: Updated the way accuracy evals works for more accurate agent-based evaluation.

Bug Fixes:

  • MCP Client Timeout: Client timeouts now work correctly and use the timeout set on parameters.

What's Changed

Full Changelog: v1.5.2...v1.5.3

Contributors

manuhortet, ashpreetbedi, and 2 other contributors
Loading

v1.5.2

20 May 18:12
@dirkbrnd dirkbrnd
v1.5.2
16e9f7a
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.
Compare
Choose a tag to compare
v1.5.2

Changelog

New Features:

  • 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.
  • Couchbase Vector DB Support: Added support for Couchbase as a vector DB for knowledge bases.
  • Knowledge Filters Update for Teams: Filters (manual + agentic) can now be used with Teams.
  • Azure Cosmos DB for MongoDB (vCore) vector db support: In the MongoDB vector db class add support for cosmosdb mongo vcore support by enabling cosmos_compatibility=True
  • Google Big Query Tools: Added Toolkit for Google BigQuery support.
  • Async Support for s3 Readers: Add async support for pdf 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.

What's Changed

New Contributors

Full Changelog: v1.5.1...v1.5.2

Contributors

misrasaurabh1, 0xRichardH, and 14 other contributors
Loading

v1.5.1

16 May 16:31
@dirkbrnd dirkbrnd
v1.5.1
1c4b0f4
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.
Compare
Choose a tag to compare
v1.5.1

Changelog

New Features:

  • Nebius Model Provider: Added Nebius as a model provider.
  • Extended Filters Support on Vector DBs: Added filtering support for other vector DBs
    • pgvector
    • Milvus
    • Weaviate
    • Chroma

Improvements:

  • Redis SSL: Added the ssl parameter to Redis storage.
  • Improve release tests workflow: add a script to do model specific minimal setup installation on release

What's Changed

New Contributors

Full Changelog: v.1.5.0...v1.5.1

Contributors

gsaada, willemcdejongh, and 4 other contributors
Loading