Griptape: Modular Python Framework for AI Agents and Workflows

Introduction

Griptape is a powerful and modular Python framework specifically engineered for building AI agents and complex workflows. It offers a comprehensive set of abstractions that streamline the development of generative AI (genAI) applications, incorporating features like chain-of-thought reasoning, robust tools, and versatile memory management. Griptape simplifies interactions with Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and other essential AI components.

The framework is built around several core components:

Structures: Organize AI logic, including Agents (for specific tasks), Pipelines (for sequential tasks), and Workflows (for parallel task execution).
Tasks: The fundamental building blocks within Structures, enabling interaction with Engines, Tools, and other Griptape components.
Memory: Facilitates information retention across interactions, with Conversation Memory, Task Memory, and Meta Memory.
Drivers: Provide a flexible interface for interacting with external resources and services, allowing easy swapping of providers for LLMs, embeddings, vector stores, web search, and more.
Tools: Equip LLMs with capabilities to interact with data and services, with both built-in and custom tool options.
Engines: Wrap Drivers to provide use-case-specific functionality, such as RAG, Extraction, Summary, and Eval Engines.

For those seeking a no-code experience, Griptape also offers Griptape Nodes, a visual desktop application for building and running AI workflows.

Installation

To get started with Griptape, you can install it directly using pip. For detailed installation instructions and environment setup, please refer to the official Griptape documentation.

pip install griptape

Examples

Hello World Example

This minimal example demonstrates how to create a simple PromptTask with an OpenAI driver and a rule, then run it to get a response.

from griptape.drivers.prompt.openai import OpenAiChatPromptDriver
from griptape.rules import Rule
from griptape.tasks import PromptTask

task = PromptTask(
    prompt_driver=OpenAiChatPromptDriver(model="gpt-4.1"),
    rules=[Rule("Keep your answer to a few sentences.")],
)

result = task.run("How do I do a kickflip?")

print(result.value)

Output:

To do a kickflip, start by positioning your front foot slightly angled near the middle of the board and your back foot on the tail. Pop the tail down with your back foot while flicking the edge of the board with your front foot to make it spin. Jump and keep your body centered over the board, then catch it with your feet and land smoothly. Practice and patience are key!

Task and Workflow Example

This example showcases a more complex workflow using Griptape to research multiple open-source projects, summarize their features, and visualize the workflow.

from griptape.drivers.prompt.openai_chat_prompt_driver import OpenAiChatPromptDriver
from griptape.drivers.web_search.duck_duck_go import DuckDuckGoWebSearchDriver
from griptape.rules import Rule, Ruleset
from griptape.structures import Workflow
from griptape.tasks import PromptTask, TextSummaryTask
from griptape.tools import WebScraperTool, WebSearchTool
from griptape.utils import StructureVisualizer
from pydantic import BaseModel


class Feature(BaseModel):
    name: str
    description: str
    emoji: str


class Output(BaseModel):
    answer: str
    key_features: list[Feature]


projects = ["griptape", "langchain", "crew-ai", "pydantic-ai"]

prompt_driver = OpenAiChatPromptDriver(model="gpt-4.1")
workflow = Workflow(
    tasks=[
        [
            PromptTask(
                id=f"project-{project}",
                input="Tell me about the open source project: {{ project }}.",
                prompt_driver=prompt_driver,
                context={"project": projects},
                output_schema=Output,
                tools=[
                    WebSearchTool(
                        web_search_driver=DuckDuckGoWebSearchDriver(),
                    ),
                    WebScraperTool(),
                ],
                child_ids=["summary"],
            )
            for project in projects
        ],
        TextSummaryTask(
            input="{{ parents_output_text }}",
            id="summary",
            rulesets=[
                Ruleset(
                    name="Format", rules=[Rule("Be detailed."), Rule("Include emojis.")]
                )
            ],
        ),
    ]
)

workflow.run()

print(StructureVisualizer(workflow).to_url())

Output:

 Output: Here's a detailed summary of the open-source projects mentioned:

 1. **Griptape** ??:                                                                                                            
    - Griptape is a modular Python framework designed for creating AI-powered applications. It focuses on securely connecting to
 enterprise data and APIs. The framework provides structured components like Agents, Pipelines, and Workflows, allowing for both
 parallel and sequential operations. It includes built-in tools and supports custom tool creation for data and service
 interaction.

 2. **LangChain** ?:
    - LangChain is a framework for building applications powered by Large Language Models (LLMs). It offers a standard interface
 for models, embeddings, and vector stores, facilitating real-time data augmentation and model interoperability. LangChain
 integrates with various data sources and external systems, making it adaptable to evolving technologies.

 3. **CrewAI** ?:
    - CrewAI is a standalone Python framework for orchestrating multi-agent AI systems. It allows developers to create and
 manage AI agents that collaborate on complex tasks. CrewAI emphasizes ease of use and scalability, providing tools and
 documentation to help developers build AI-powered solutions.

 4. **Pydantic-AI** ?:
    - Pydantic-AI is a Python agent framework that simplifies the development of production-grade applications with Generative
 AI. Built on Pydantic, it supports various AI models and provides features like type-safe design, structured response
 validation, and dependency injection. Pydantic-AI aims to bring the ease of FastAPI development to AI applications.

 These projects offer diverse tools and frameworks for developing AI applications, each with unique features and capabilities
 tailored to different aspects of AI development.

Why Use Griptape?

Griptape stands out as an excellent choice for developing generative AI applications due to its modular design and comprehensive feature set. It provides a structured yet flexible approach to building AI agents and workflows, making complex tasks manageable. With its extensive array of drivers, Griptape offers seamless integration with various LLMs, vector stores, and external services, ensuring high adaptability. The framework's focus on clear abstractions for components like memory, tools, and engines empowers developers to create robust, scalable, and intelligent AI solutions with greater efficiency.