- Changed `add_datetime_to_instructions` to `add_datetime_to_context` in travel planner for better context handling.
- Updated response type to `RunOutput` in both travel planner and GitHub agent for improved type safety.
- Specified minimum version for the 'agno' package in requirements.txt for compatibility.
- Changed import path for OllamaEmbedder to reflect new Agno structure.
- Switched from show_tool_calls to debug_mode for improved debugging experience.
- Replaced PDFUrlKnowledgeBase with Knowledge class for improved document management.
- Updated to use AgentOS for the application interface instead of Playground.
- Adjusted README to reflect changes in the interface and knowledge base loading process.
- Specified minimum version for the 'agno' package in requirements.txt.
- Replaced Claude model with Gemini for improved language processing.
- Updated knowledge management by replacing UrlKnowledge with Knowledge class.
- Enhanced session state handling to prevent duplicate URL loading.
- Adjusted README to reflect changes in API key requirements and default knowledge sources.
- Updated requirements.txt to specify a minimum version for the 'agno' package.
- Replaced UrlKnowledge with Knowledge for better document loading.
- Enhanced session state management for URLs to prevent duplicates.
- Updated placeholder URLs and query prompts for clarity.
- Adjusted requirements.txt to specify a minimum version for the 'agno' package.
- Replaced PDFUrlKnowledgeBase with Knowledge for managing document loading.
- Enhanced URL management by adding a check to prevent duplicate URLs in session state.
- Updated requirements.txt to specify a minimum version for the 'agno' package.
- Changed the output type from unspecified to RunOutput in the local travel agent.
- Updated context handling by changing 'add_datetime_to_instructions' to 'add_datetime_to_context' in both local travel agent and travel agent files.
- Changed the output type from RunResponse to RunOutput in the music generator agent.
- Updated requirements.txt to specify a minimum version for the 'agno' package.
- Changed model ID from "gemini-2.0-flash" to "gemini-2.5-pro" for improved performance.
- Specified the type of response from the medical agent's run method as RunOutput.
- Updated requirements.txt to enforce a minimum version for the 'agno' package.
- Changed function parameter names from 'message' to more descriptive names in ai_breakup_recovery_agent.py.
- Updated README with correct repository URL and streamlined installation instructions.
- Modified requirements.txt to specify a minimum version for the 'agno' package.
- Updated Streamlit UI for better user experience with API key inputs and blog URL entry.
- Enhanced podcast generation process by integrating ElevenLabs for audio output.
- Improved error handling and summary display for generated podcasts.
- Updated requirements to ensure compatibility with newer library versions.
What it does
- Pins all core dependencies in `requirements.txt` to specific versions to ensure environment stability and prevent future breaking changes.
- Adds `langchain-text-splitters==1.0.0` and updates code to use the compatible import instead of the deprecated `langchain.text_splitter`.
- Ensures the app runs consistently across different environments and with the current versions of OpenAI and LangChain libraries.
- Introduced a new multi-agent system for analyzing landing page designs and providing expert UI/UX feedback.
- Implemented a Coordinator/Dispatcher pattern with specialized agents for visual analysis, design strategy, and visual implementation.
- Added tools for editing and generating improved landing pages, along with comprehensive reporting features.
- Added Parlant as a new sponsor with updated link and image.
- Adjusted image height for Unblocked sponsor for better display consistency.
- Included a sponsorship badge to encourage support.
- Introduced a multi-agent system for home renovation planning that analyzes photos and generates personalized renovation plans.
- Implemented a Coordinator/Dispatcher pattern with specialized agents for visual assessment, design planning, and project coordination.
- Added tools for generating and editing photorealistic renderings, along with budget-aware planning features.
- Updated the email generation workflow to yield progress updates during company processing.
- Refactored the database integration to use SqliteDb for better management.
- Enhanced the user interface with a more structured display of generated emails, company research, and contact information.
- Added troubleshooting tips in case of no email generation.
- Updated README with detailed features, installation instructions, and usage guide.
- Increased agno package version requirement to 2.0.4 for compatibility.
- Replaced Node.js MCP server with the official GitHub MCP server running in Docker.
- Added OpenAI API key input for enhanced query processing.
- Updated README to reflect new requirements and usage instructions.
- Introduced a new multi-agent system for web research, including a main coordinator agent and specialized research and summary agents.
- Added detailed README for setup, usage, and agent configuration.
