Awesome AI AgentsLLM Framework Tools

Undertone0809/promptulate

⭐ 512 Python added to this list on 2025-03-09 repository created 2023-03-18

Promptulate is a lightweight and efficient framework designed for developing Large Language Model (LLM) automation and autonomous language agents. It offers a Pythonic development experience, enabling developers to build AI agent applications with minimal code. The framework integrates the best practices and features from various open-source projects to lower the entry barrier and unify development standards. Promptulate supports a wide range of LLMs and provides diverse agent types such as WebAgent, ToolAgent, and CodeAgent, which can plan, reason, and act to solve complex problems. It allows seamless integration with tools from other frameworks like LangChain, reducing integration costs. Any Python function can be converted into a tool for agents, simplifying tool creation and usage. The framework includes lifecycle management and hooks for customization at different stages of agents, tools, and LLMs. It supports terminal integration for rapid debugging and prompt caching to improve efficiency. Promptulate also features a powerful OpenAI wrapper that replaces the need for the OpenAI SDK, streamlining development. Additionally, it offers integration with Streamlit components for quick prototyping and reusable UI elements. The framework supports nearly all major LLM providers and models through its integration with litellm, including OpenAI, Azure, AWS, Google, Huggingface, and many others. This extensive model compatibility allows developers to easily switch or customize models according to their needs. The core philosophy of Promptulate is to provide a simple, pythonic, and efficient way to build AI applications, focusing on ease of use and minimal code requirements. The main interface, pne.chat(), encapsulates most functionalities, enabling developers to create sophisticated AI applications quickly and effectively.

https://github.com/Undertone0809/promptulate

agentai-agentai-application-developmentautogenautonomous-agentschatgptcodeagentgpt-4langchainlangchain-integrationlanguage-agentlarge-language-modellifecycle-hookslitellmllmmodel-compatibilityopenai-wrapperpnepromptprompt-cachingprompt-engineeringpromptulatepythonpythonic-frameworkstreamlit-integrationterminal-integrationtool-integrationtoolagentwebagent

Also in LLM Framework Tools

mudler/LocalAI

LocalAI is an open-source AI engine that enables running various AI models (LLMs, vision, voice, image, video) on any hardware, including CPU-only systems, with a composable and extensible architec...

langfuse/langfuse

Langfuse is an open source LLM engineering platform that enables collaborative development, monitoring, evaluation, and debugging of AI applications with comprehensive observability, prompt management, and integration features.

567-labs/instructor

Instructor is a popular Python library that simplifies working with structured outputs from large language models by providing validation, retries, and streaming support across multiple LLM providers.

TEN-framework/ten-framework

TEN Framework is a real-time, distributed, cloud-edge collaborative multimodal AI agent framework supporting multiple programming languages for building high-performance AI applications.

google/adk-samples

A collection of sample agents built with the Agent Development Kit (ADK) to accelerate development of conversational and multi-agent workflows, designed for customization and integration with Google Cloud services.

truefoundry/cognita

Cognita is an open-source, modular, and production-ready RAG framework by TrueFoundry that simplifies building, customizing, and deploying scalable Retrieval Augmented Generation applications with a no-code UI and extensive integration features.

lemony-ai/cascadeflow

In-process Python and TypeScript library that cascades model calls inside the agent loop, routing each query or tool call between small and flagship models by quality, cost, latency and budget.

shroominic/codeinterpreter-api

An open-source API that implements the ChatGPT Code Interpreter for sandboxed Python code execution, enabling data analysis, visualization, and interactive AI-driven computational tasks with local execution and scalable production deployment.