3 posts tagged with "AI Agents"
View All TagsAI Agents can now connect to MCP servers, enabling them to execute any tool made available by the MCP server.
New features
- Connect MCP servers to AI Agents
AI Agents in flows now support a chat mode interface with conversation history and memory capabilities.
New features
- Chat mode toggle on flow inputs that transforms the flow interface into a chat UI.
- Support for multiple different conversations within the chat interface.
- New messages_context_length configuration option for AI agents to remember past conversations.
- Persistent conversation history across flow executions for continuous interactions.
Integrate AI agents directly into your Windmill flows with comprehensive support for all major AI providers, multimodal capabilities, streaming responses, tool integration, and structured outputs. AI agents can process text and images, call Windmill scripts as tools, stream responses in real-time, and output structured data following JSON schemas.
New features
- Support for all major AI providers including OpenAI, Azure OpenAI, Anthropic, Mistral, DeepSeek, Google AI (Gemini), Groq, OpenRouter, Together AI, and custom AI endpoints.
- Real-time streaming responses with detailed payload types including token deltas, tool calls, tool execution, and tool results.
- Tool integration allowing AI agents to call Windmill scripts (inline, workspace, or Hub scripts) as tools for extended functionality.
- Image input support for AI analysis and processing of uploaded images (requires S3 object storage configuration).
- Structured output generation respecting JSON schemas for predictable, processable responses.