Skip to main content

Meet Tyler

A framework for manifesting AI agents with a complete lack of conventional limitations.​

Tyler makes it easy to start building effective AI agents in just a few lines of code. Tyler provides all the essential components needed to build production-ready AI agents that can understand context, manage conversations, and effectively use tools.

Key Features​

  • Multimodal support: Process and understand images, audio, PDFs, and more out of the box
  • Ready-to-use tools: Comprehensive set of built-in tools with easy integration of custom built tools
  • MCP compatibility: Seamless integration with Model Context Protocol (MCP) compatible servers and tools
  • Real-time streaming: Build interactive applications with streaming responses from both the assistant and tools
  • Structured data model: Built-in support for threads, messages, and attachments to maintain conversation context
  • Persistent storage: Choose between in-memory, SQLite, or PostgreSQL to store conversation history and files
  • Advanced debugging: Integration with W&B Weave for powerful tracing and debugging capabilities
  • Flexible model support: Use any LLM provider supported by LiteLLM (100+ providers including OpenAI, Anthropic, etc.)

Get started quickly by installing Tyler via pip: pip install tyler-agent and check out our quickstart guide to build your first agent in minutes.

Overview​



Chat with Tyler

While Tyler can be used as a library, it also has a web-based chat interface that allows you to interact with your agent. The interface is available as a separate repository at tyler-chat.

Chat with Tyler Interface

Key features of Chat with Tyler​

  • Modern, responsive web interface
  • Real-time interaction with Tyler agents
  • Support for file attachments
  • Message history and context preservation
  • Easy deployment and customization

To get started with the chat interface, visit the Chat with Tyler documentation.

Next Steps​