griptape

Modular Python framework for AI agents and workflows with chain-of-thought reasoning, tools, and memory.

Stars: 1968

Visit

Griptape is a modular Python framework for building AI-powered applications that securely connect to your enterprise data and APIs. It offers developers the ability to maintain control and flexibility at every step. Griptape's core components include Structures (Agents, Pipelines, and Workflows), Tasks, Tools, Memory (Conversation Memory, Task Memory, and Meta Memory), Drivers (Prompt and Embedding Drivers, Vector Store Drivers, Image Generation Drivers, Image Query Drivers, SQL Drivers, Web Scraper Drivers, and Conversation Memory Drivers), Engines (Query Engines, Extraction Engines, Summary Engines, Image Generation Engines, and Image Query Engines), and additional components (Rulesets, Loaders, Artifacts, Chunkers, and Tokenizers). Griptape enables developers to create AI-powered applications with ease and efficiency.

README:

🛠️ Core Components

🏗️ Structures

🤖 Agents consist of a single Task.
🔄 Pipelines organize a sequence of Tasks so that the output from one Task may flow into the next.
🌐 Workflows configure Tasks to operate in parallel.

📝 Tasks

Tasks are the core building blocks within Structures, enabling interaction with Engines, Tools, and other Griptape components.

🔧 Tools

Tools provide capabilities for LLMs to interact with data and services. Griptape includes a variety of built-in Tools, and makes it easy to create custom Tools.

🧠 Memory

💬 Conversation Memory enables LLMs to retain and retrieve information across interactions.
🗃️ Task Memory keeps large or sensitive Task outputs off the prompt that is sent to the LLM.
📊 Meta Memory enables passing in additional metadata to the LLM, enhancing the context and relevance of the interaction.

🚗 Drivers

Drivers facilitate interactions with external resources and services:

🗣️ Prompt Drivers manage textual interactions with LLMs.
🔢 Embedding Drivers generate vector embeddings from textual inputs.
💾 Vector Store Drivers manage the storage and retrieval of embeddings.
🎨 Image Generation Drivers create images from text descriptions.
🔎 Image Query Drivers query images from text queries.
💼 SQL Drivers interact with SQL databases.
🌐 Web Scraper Drivers extract information from web pages.
🧠 Conversation Memory Drivers manage the storage and retrieval of conversational data.

🚂 Engines

Engines wrap Drivers and provide use-case-specific functionality:

📊 RAG Engine is an abstraction for implementing modular Retrieval Augmented Generation (RAG) pipelines.
🛠️ Extraction Engines extract JSON or CSV data from unstructured text.
📝 Summary Engines generate summaries from textual content.
🖼️ Image Generation Engines generate images from textual descriptions.
🔎 Image Query Engines query images based on textual prompts.

📦 Additional Components

📐 Rulesets steer LLM behavior with minimal prompt engineering.
🔄 Loaders load data from various sources.
🏺 Artifacts allow for passing data of different types between Griptape components.
✂️ Chunkers segment texts into manageable pieces for diverse text types.
🔢 Tokenizers count the number of tokens in a text to not exceed LLM token limits.

Documentation

Please refer to Griptape Docs for:

Getting started guides.
Core concepts and design overviews.
Examples.
Contribution guidelines.

Please check out Griptape Trade School for free online courses.

Quick Start

First, install griptape:

pip install "griptape[all]" -U

Second, configure an OpenAI client by getting an API key and adding it to your environment as OPENAI_API_KEY. By default, Griptape uses OpenAI Chat Completions API to execute LLM prompts.

With Griptape, you can create Structures, such as Agents, Pipelines, and Workflows, composed of different types of Tasks. Let's build a simple creative Agent that dynamically uses three tools and moves the data around in Task Memory.

from griptape.structures import Agent
from griptape.tools import WebScraperTool, FileManagerTool, PromptSummaryTool

agent = Agent(
    input="Load {{ args[0] }}, summarize it, and store it in a file called {{ args[1] }}.",
    tools=[
        WebScraperTool(off_prompt=True),
        PromptSummaryTool(off_prompt=True),
        FileManagerTool()
    ]
)
agent.run("https://griptape.ai", "griptape.txt")

And here is the output:

[08/12/24 14:48:15] INFO     ToolkitTask c90d263ec69046e8b30323c131ae4ba0
                             Input: Load https://griptape.ai, summarize it, and store it in a file called griptape.txt.
[08/12/24 14:48:16] INFO     Subtask ebe23832cbe2464fb9ecde9fcee7c30f
                             Actions: [
                               {
                                 "tag": "call_62kBnkswnk9Y6GH6kn1GIKk6",
                                 "name": "WebScraperTool",
                                 "path": "get_content",
                                 "input": {
                                   "values": {
                                     "url": "https://griptape.ai"
                                   }
                                 }
                               }
                             ]
[08/12/24 14:48:17] INFO     Subtask ebe23832cbe2464fb9ecde9fcee7c30f
                             Response: Output of "WebScraperTool.get_content" was stored in memory with memory_name "TaskMemory" and artifact_namespace
                             "cecca28eb0c74bcd8c7119ed7f790c95"
[08/12/24 14:48:18] INFO     Subtask dca04901436d49d2ade86cd6b4e1038a
                             Actions: [
                               {
                                 "tag": "call_o9F1taIxHty0mDlWLcAjTAAu",
                                 "name": "PromptSummaryTool",
                                 "path": "summarize",
                                 "input": {
                                   "values": {
                                     "summary": {
                                       "memory_name": "TaskMemory",
                                       "artifact_namespace": "cecca28eb0c74bcd8c7119ed7f790c95"
                                     }
                                   }
                                 }
                               }
                             ]
[08/12/24 14:48:21] INFO     Subtask dca04901436d49d2ade86cd6b4e1038a
                             Response: Output of "PromptSummaryTool.summarize" was stored in memory with memory_name "TaskMemory" and artifact_namespace
                             "73765e32b8404e32927822250dc2ae8b"
[08/12/24 14:48:22] INFO     Subtask c233853450fb4fd6a3e9c04c52b33bf6
                             Actions: [
                               {
                                 "tag": "call_eKvIUIw45aRYKDBpT1gGKc9b",
                                 "name": "FileManagerTool",
                                 "path": "save_memory_artifacts_to_disk",
                                 "input": {
                                   "values": {
                                     "dir_name": ".",
                                     "file_name": "griptape.txt",
                                     "memory_name": "TaskMemory",
                                     "artifact_namespace": "73765e32b8404e32927822250dc2ae8b"
                                   }
                                 }
                               }
                             ]
                    INFO     Subtask c233853450fb4fd6a3e9c04c52b33bf6
                             Response: Successfully saved memory artifacts to disk
[08/12/24 14:48:23] INFO     ToolkitTask c90d263ec69046e8b30323c131ae4ba0
                             Output: The content from https://griptape.ai has been summarized and stored in a file called `griptape.txt`.

During the run, the Griptape Agent loaded a webpage with a Tool, stored its full content in Task Memory, queried it to answer the original question, and finally saved the answer to a file.

The important thing to note here is that no matter how big the webpage is it can never blow up the prompt token limit because the full content of the page never goes back to the LLM. Additionally, no data from the subsequent subtasks were returned back to the prompt either. So, how does it work?

In the above example, we set off_prompt to True, which means that the LLM can never see the data it manipulates, but can send it to other Tools.

[!IMPORTANT]
This example uses Griptape's ToolkitTask, which requires a highly capable LLM to function correctly. By default, Griptape uses the OpenAiChatPromptDriver; for another powerful LLM try swapping to the AnthropicPromptDriver! If you're using a less powerful LLM, consider using the ToolTask instead, as the ToolkitTask might not work properly or at all.

Check out our docs to learn more about how to use Griptape with other LLM providers like Anthropic, Claude, Hugging Face, and Azure.

Versioning

Griptape is in constant development and its APIs and documentation are subject to change. Until we stabilize the API and release version 1.0.0, we will use minor versions (i.e., x.Y.z) to introduce features and breaking features, and patch versions (i.e., x.y.Z) for bug fixes.

Contributing

Thank you for considering contributing to Griptape! Before you start, please read the following guidelines.

Submitting Issues

If you have identified a bug, want to propose a new feature, or have a question, please submit an issue through our public issue tracker. Before submitting a new issue, please check the existing issues to ensure it hasn't been reported or discussed before.

Submitting Pull Requests

We welcome and encourage pull requests. To streamline the process, please follow these guidelines:

Existing Issues: Please submit pull requests only for existing issues. If you want to work on new functionality or fix a bug that hasn't been addressed yet, please first submit an issue. This allows the Griptape team to internally process the request and provide a public response.
Branch: Submit all pull requests to the dev branch. This helps us manage changes and integrate them smoothly.
Unit Tests: Ensure that your pull request passes all existing unit tests. Additionally, if you are introducing new code, please include new unit tests to validate its functionality.

Run make test/unit to execute the test suite locally.

Documentation: Every pull request must include updates to documentation or explicitly explain why a documentation update is not required. Documentation is crucial for maintaining a comprehensive and user-friendly project.

Run make docs to build the documentation locally.

Code Checks: Griptape a variety of tools to enforce code quality and style. Your code must pass all checks before it can be merged.

Run make check to run all code checks locally.

Changelog: If your pull request introduces a notable change, please update the changelog.

New Griptape Tools

Griptape's extensibility allows anyone to develop and distribute tools independently. With rare exceptions for Tools providing broadly applicable functionality, new Griptape Tools should be managed as their own projects and not submitted to the core framework. Pull requests for new tools (unless addressing an existing issue) will be closed.

The Griptape Tool Template provides the recommended structure, step-by-step instructions, basic automation, and usage examples for new Tools. In the Template, select Use this template then Create a new repository to begin a new Tool project.

Dev and Test Dependencies

Install all dependencies via Make:

make install

Or install by calling Poetry directly:

poetry install --all-extras --with dev --with test --with docs

Configure pre-commit to ensure that your code is formatted correctly and passes all checks:

poetry run pre-commit install

License

Griptape is available under the Apache 2.0 License.

For Tasks:

Click tags to check more tools for each tasks

build ai applications connect to enterprise data manage ai models deploy ai models monitor ai models

For Jobs:

ai engineer data scientist machine learning engineer software engineer research scientist

Alternative AI tools for griptape

Similar Open Source Tools

griptape

github

: 2.0k

typechat.net

TypeChat.NET is a framework that provides cross-platform libraries for building natural language interfaces with language models using strong types, type validation, and simple type-safe programs. It translates user intent into strongly typed objects and JSON programs, with support for schema export, extensibility, and common scenarios. The framework is actively developed with frequent updates, evolving based on exploration and feedback. It consists of assemblies for translating user intent, synthesizing JSON programs, and integrating with Microsoft Semantic Kernel. TypeChat.NET requires familiarity with and access to OpenAI language models for its examples and scenarios.

github

: 181

chroma

Chroma is an open-source embedding database that provides a simple, scalable, and feature-rich way to build Python or JavaScript LLM apps with memory. It offers a fully-typed, fully-tested, and fully-documented API that makes it easy to get started and scale your applications. Chroma also integrates with popular tools like LangChain and LlamaIndex, and supports a variety of embedding models, including Sentence Transformers, OpenAI embeddings, and Cohere embeddings. With Chroma, you can easily add documents to your database, query relevant documents with natural language, and compose documents into the context window of an LLM like GPT3 for additional summarization or analysis.

github

: 14.9k

spacy-llm

This package integrates Large Language Models (LLMs) into spaCy, featuring a modular system for **fast prototyping** and **prompting** , and turning unstructured responses into **robust outputs** for various NLP tasks, **no training data** required. It supports open-source LLMs hosted on Hugging Face 🤗: Falcon, Dolly, Llama 2, OpenLLaMA, StableLM, Mistral. Integration with LangChain 🦜️🔗 - all `langchain` models and features can be used in `spacy-llm`. Tasks available out of the box: Named Entity Recognition, Text classification, Lemmatization, Relationship extraction, Sentiment analysis, Span categorization, Summarization, Entity linking, Translation, Raw prompt execution for maximum flexibility. Soon: Semantic role labeling. Easy implementation of **your own functions** via spaCy's registry for custom prompting, parsing and model integrations. For an example, see here. Map-reduce approach for splitting prompts too long for LLM's context window and fusing the results back together

github

: 948

restai

RestAI is an AIaaS (AI as a Service) platform that allows users to create and consume AI agents (projects) using a simple REST API. It supports various types of agents, including RAG (Retrieval-Augmented Generation), RAGSQL (RAG for SQL), inference, vision, and router. RestAI features automatic VRAM management, support for any public LLM supported by LlamaIndex or any local LLM supported by Ollama, a user-friendly API with Swagger documentation, and a frontend for easy access. It also provides evaluation capabilities for RAG agents using deepeval.

github

: 361

VedAstro

VedAstro is an open-source Vedic astrology tool that provides accurate astrological predictions and data. It offers a user-friendly website, a chat API, an open API, a JavaScript SDK, a Swiss Ephemeris API, and a machine learning table generator. VedAstro is free to use and is constantly being updated with new features and improvements.

github

: 222

uAgents

uAgents is a Python library developed by Fetch.ai that allows for the creation of autonomous AI agents. These agents can perform various tasks on a schedule or take action on various events. uAgents are easy to create and manage, and they are connected to a fast-growing network of other uAgents. They are also secure, with cryptographically secured messages and wallets.

github

: 951

litlytics

LitLytics is an affordable analytics platform leveraging LLMs for automated data analysis. It simplifies analytics for teams without data scientists, generates custom pipelines, and allows customization. Cost-efficient with low data processing costs. Scalable and flexible, works with CSV, PDF, and plain text data formats.

github

: 83

UFO

UFO is a UI-focused dual-agent framework to fulfill user requests on Windows OS by seamlessly navigating and operating within individual or spanning multiple applications.

github

: 7.5k

llm-answer-engine

This repository contains the code and instructions needed to build a sophisticated answer engine that leverages the capabilities of Groq, Mistral AI's Mixtral, Langchain.JS, Brave Search, Serper API, and OpenAI. Designed to efficiently return sources, answers, images, videos, and follow-up questions based on user queries, this project is an ideal starting point for developers interested in natural language processing and search technologies.

github

: 4.5k

llm-autoeval

LLM AutoEval is a tool that simplifies the process of evaluating Large Language Models (LLMs) using a convenient Colab notebook. It automates the setup and execution of evaluations using RunPod, allowing users to customize evaluation parameters and generate summaries that can be uploaded to GitHub Gist for easy sharing and reference. LLM AutoEval supports various benchmark suites, including Nous, Lighteval, and Open LLM, enabling users to compare their results with existing models and leaderboards.

github

: 398

crewAI

crewAI is a cutting-edge framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks. It provides a flexible and structured approach to AI collaboration, enabling users to define agents with specific roles, goals, and tools, and assign them tasks within a customizable process. crewAI supports integration with various LLMs, including OpenAI, and offers features such as autonomous task delegation, flexible task management, and output parsing. It is open-source and welcomes contributions, with a focus on improving the library based on usage data collected through anonymous telemetry.

github

: 17.2k

baml

BAML is a config file format for declaring LLM functions that you can then use in TypeScript or Python. With BAML you can Classify or Extract any structured data using Anthropic, OpenAI or local models (using Ollama) ## Resources ![](https://img.shields.io/discord/1119368998161752075.svg?logo=discord&label=Discord%20Community) [Discord Community](https://discord.gg/boundaryml) ![](https://img.shields.io/twitter/follow/boundaryml?style=social) [Follow us on Twitter](https://twitter.com/boundaryml) * Discord Office Hours - Come ask us anything! We hold office hours most days (9am - 12pm PST). * Documentation - Learn BAML * Documentation - BAML Syntax Reference * Documentation - Prompt engineering tips * Boundary Studio - Observability and more #### Starter projects * BAML + NextJS 14 * BAML + FastAPI + Streaming ## Motivation Calling LLMs in your code is frustrating: * your code uses types everywhere: classes, enums, and arrays * but LLMs speak English, not types BAML makes calling LLMs easy by taking a type-first approach that lives fully in your codebase: 1. Define what your LLM output type is in a .baml file, with rich syntax to describe any field (even enum values) 2. Declare your prompt in the .baml config using those types 3. Add additional LLM config like retries or redundancy 4. Transpile the .baml files to a callable Python or TS function with a type-safe interface. (VSCode extension does this for you automatically). We were inspired by similar patterns for type safety: protobuf and OpenAPI for RPCs, Prisma and SQLAlchemy for databases. BAML guarantees type safety for LLMs and comes with tools to give you a great developer experience: ![](docs/images/v3/prompt_view.gif) Jump to BAML code or how Flexible Parsing works without additional LLM calls. | BAML Tooling | Capabilities | | ----------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | BAML Compiler install | Transpiles BAML code to a native Python / Typescript library (you only need it for development, never for releases) Works on Mac, Windows, Linux ![](https://img.shields.io/badge/Python-3.8+-default?logo=python)![](https://img.shields.io/badge/Typescript-Node_18+-default?logo=typescript) | | VSCode Extension install | Syntax highlighting for BAML files Real-time prompt preview Testing UI | | Boundary Studio open (not open source) | Type-safe observability Labeling |

github

: 1.1k

peridyno

PeriDyno is a CUDA-based, highly parallel physics engine targeted at providing real-time simulation of physical environments for intelligent agents. It is designed to be easy to use and integrate into existing projects, and it provides a wide range of features for simulating a variety of physical phenomena. PeriDyno is open source and available under the Apache 2.0 license.

github

: 230

bittensor

Bittensor is an internet-scale neural network that incentivizes computers to provide access to machine learning models in a decentralized and censorship-resistant manner. It operates through a token-based mechanism where miners host, train, and procure machine learning systems to fulfill verification problems defined by validators. The network rewards miners and validators for their contributions, ensuring continuous improvement in knowledge output. Bittensor allows anyone to participate, extract value, and govern the network without centralized control. It supports tasks such as generating text, audio, images, and extracting numerical representations.

github

: 886

agent-contributions-library

The AI Agents Contributions Library is a repository dedicated to managing datasets on voice and cognitive core data for AI agents within the Virtual DAO ecosystem. It provides a structured framework for recording, reviewing, and rewarding contributions from contributors. The repository includes folders for character cards, contribution datasets, fine-tuning resources, text datasets, and voice datasets. Contributors can submit datasets following specific guidelines and formats, and the Virtual DAO team reviews and integrates approved datasets to enhance AI agents' capabilities.

github

: 77

For similar tasks

griptape

github

: 2.0k

AI-in-a-Box

AI-in-a-Box is a curated collection of solution accelerators that can help engineers establish their AI/ML environments and solutions rapidly and with minimal friction, while maintaining the highest standards of quality and efficiency. It provides essential guidance on the responsible use of AI and LLM technologies, specific security guidance for Generative AI (GenAI) applications, and best practices for scaling OpenAI applications within Azure. The available accelerators include: Azure ML Operationalization in-a-box, Edge AI in-a-box, Doc Intelligence in-a-box, Image and Video Analysis in-a-box, Cognitive Services Landing Zone in-a-box, Semantic Kernel Bot in-a-box, NLP to SQL in-a-box, Assistants API in-a-box, and Assistants API Bot in-a-box.

github

: 527

spring-ai

The Spring AI project provides a Spring-friendly API and abstractions for developing AI applications. It offers a portable client API for interacting with generative AI models, enabling developers to easily swap out implementations and access various models like OpenAI, Azure OpenAI, and HuggingFace. Spring AI also supports prompt engineering, providing classes and interfaces for creating and parsing prompts, as well as incorporating proprietary data into generative AI without retraining the model. This is achieved through Retrieval Augmented Generation (RAG), which involves extracting, transforming, and loading data into a vector database for use by AI models. Spring AI's VectorStore abstraction allows for seamless transitions between different vector database implementations.

github

: 3.1k

ragstack-ai

RAGStack is an out-of-the-box solution simplifying Retrieval Augmented Generation (RAG) in GenAI apps. RAGStack includes the best open-source for implementing RAG, giving developers a comprehensive Gen AI Stack leveraging LangChain, CassIO, and more. RAGStack leverages the LangChain ecosystem and is fully compatible with LangSmith for monitoring your AI deployments.

github

: 127

breadboard

Breadboard is a library for prototyping generative AI applications. It is inspired by the hardware maker community and their boundless creativity. Breadboard makes it easy to wire prototypes and share, remix, reuse, and compose them. The library emphasizes ease and flexibility of wiring, as well as modularity and composability.

github

: 176

cloudflare-ai-web

Cloudflare-ai-web is a lightweight and easy-to-use tool that allows you to quickly deploy a multi-modal AI platform using Cloudflare Workers AI. It supports serverless deployment, password protection, and local storage of chat logs. With a size of only ~638 kB gzip, it is a great option for building AI-powered applications without the need for a dedicated server.

github

: 1.9k

app-builder

AppBuilder SDK is a one-stop development tool for AI native applications, providing basic cloud resources, AI capability engine, Qianfan large model, and related capability components to improve the development efficiency of AI native applications.

github

: 448

cookbook

This repository contains community-driven practical examples of building AI applications and solving various tasks with AI using open-source tools and models. Everyone is welcome to contribute, and we value everybody's contribution! There are several ways you can contribute to the Open-Source AI Cookbook: Submit an idea for a desired example/guide via GitHub Issues. Contribute a new notebook with a practical example. Improve existing examples by fixing issues/typos. Before contributing, check currently open issues and pull requests to avoid working on something that someone else is already working on.

github

: 1.6k

For similar jobs

sweep

Sweep is an AI junior developer that turns bugs and feature requests into code changes. It automatically handles developer experience improvements like adding type hints and improving test coverage.

github

: 7.1k

teams-ai

The Teams AI Library is a software development kit (SDK) that helps developers create bots that can interact with Teams and Microsoft 365 applications. It is built on top of the Bot Framework SDK and simplifies the process of developing bots that interact with Teams' artificial intelligence capabilities. The SDK is available for JavaScript/TypeScript, .NET, and Python.

github

: 390

ai-guide

This guide is dedicated to Large Language Models (LLMs) that you can run on your home computer. It assumes your PC is a lower-end, non-gaming setup.

github

: 159

classifai

Supercharge WordPress Content Workflows and Engagement with Artificial Intelligence. Tap into leading cloud-based services like OpenAI, Microsoft Azure AI, Google Gemini and IBM Watson to augment your WordPress-powered websites. Publish content faster while improving SEO performance and increasing audience engagement. ClassifAI integrates Artificial Intelligence and Machine Learning technologies to lighten your workload and eliminate tedious tasks, giving you more time to create original content that matters.

github

: 572

chatbot-ui

Chatbot UI is an open-source AI chat app that allows users to create and deploy their own AI chatbots. It is easy to use and can be customized to fit any need. Chatbot UI is perfect for businesses, developers, and anyone who wants to create a chatbot.

github

: 27.7k

BricksLLM

BricksLLM is a cloud native AI gateway written in Go. Currently, it provides native support for OpenAI, Anthropic, Azure OpenAI and vLLM. BricksLLM aims to provide enterprise level infrastructure that can power any LLM production use cases. Here are some use cases for BricksLLM: * Set LLM usage limits for users on different pricing tiers * Track LLM usage on a per user and per organization basis * Block or redact requests containing PIIs * Improve LLM reliability with failovers, retries and caching * Distribute API keys with rate limits and cost limits for internal development/production use cases * Distribute API keys with rate limits and cost limits for students

github

: 897

uAgents

github

: 951

griptape

github

: 2.0k