Skip to main content

Introduction

Build, orchestrate, and deploy AI solutions with ease.

What is Timbal?​

Timbal is an open-source framework for designing autonomous AI applications with flexible orchestration, real-time streaming, and multi-provider support.

Timbal empowers developers with both high-level simplicity and precise low-level control, ideal for creating autonomous AI applications tailored to any scenario.

Timbal provides two main patterns for building AI applications:

  • Agentic (Agent-based): LLMs autonomously decide execution paths and tool usage based on goals. Best for:

    • Complex reasoning tasks
    • Dynamic tool selection
    • Open-ended problem solving
    from timbal import Agent
    

    agent = Agent(
        model="gpt-4.1",
        tools=[search_web],
    )

  • Workflow (Flow-based): You explicitly define the execution steps and tool usage. Ideal for:

    • Predictable processes
    • Strict control requirements
    • Performance-critical applications
    from timbal import Flow
    

    # Document Database Creation Flow
    flow = (Flow()
      # Extract text from uploaded files
      .add_step(extract_text)
      .set_input("extract_text.file", "file")
      # Process and clean extracted text
      .add_step(text_processor)
      .set_input("text_processor.raw_text", "extract_text.return")
      # Convert processed text to searchable database
      .add_step(convert_to_database)
      .set_input("convert_to_database.text", "text_processor.processed_text")
      .set_input("convert_to_database.chunk_size", 1000)
      # Return database information
      .set_output("convert_to_database.return", "database_id")
    )

    You can create Flows and compose them together to create complex applications.

Choose the pattern that best aligns with your application's requirements for control, flexibility, and predictability.

Key Features​

Flow-based Orchestration

Build complex applications by composing LLM calls and tools into reusable flows.

Flexible Tools

Equip agents with custom tools and APIs to interact with external services.

Streaming Support

Real-time streaming responses and updates from LLM interactions

Task Management

Define sequential or parallel workflows with DAG architecture, automatically handling task dependencies and execution order.

Memory Management

Built-in state persistence and memory handling across interactions for contextual awareness and continuity.

Multi-Provider Support

Seamlessly integrate with leading LLM providers including OpenAI, Anthropic, Gemini, and TogetherAI.

Why Choose Timbal?​

Timbal solves the real problems you face when building AI applications:

  • Build Complex Apps Faster: Create a complete AI agent in 5 lines of code.

  • Provider-Agnostic: Switch between the best LLM provider for each step of your application.

  • Modular Architecture: Easily integrate new tools, roles, and functionalities.

  • Optimized for Deployment: Designed for scalability and reliability in real-world use cases.

  • Security in Mind: Built to meet the rigorous demands of enterprise-level security.

  • Cost-Efficient: Optimized to minimize token usage and API calls

Don't waste time reinventing the wheel: Timbal gives you everything you need to build serious AI applications today.