Awesome AI Agents › Stateful Serverless Frameworks
Mirascope is a versatile and user-friendly library designed to simplify interactions with large language models (LLMs) through a unified interface. It supports multiple LLM providers such as OpenAI, Anthropic, Mistral, Google (Gemini/Vertex), Groq, Cohere, LiteLLM, Azure AI, and Bedrock, allowing developers to work seamlessly across different platforms. The library facilitates various AI-driven tasks including text generation, structured information extraction, and the development of complex agent systems. Mirascope aims to streamline the development process by providing powerful tools that abstract the complexities of working with different LLM providers, making it easier to build robust AI applications. The project offers a quickstart guide that demonstrates how to install the library, set API keys, and make calls to LLMs for tasks such as extracting book titles and authors from unstructured text. It uses Python and integrates with Pydantic for data validation and modeling. The library is well-documented with tutorials and comprehensive guides available on its website, helping users to get started quickly and explore advanced features. Mirascope follows semantic versioning and is licensed under the MIT License, ensuring it is open and accessible for developers. The project also includes continuous integration with tests and coverage badges, indicating a focus on code quality and reliability. Overall, Mirascope provides a flexible and efficient solution for developers looking to leverage the power of LLMs across multiple providers without being hindered by provider-specific complexities.
https://github.com/Mirascope/mirascope
LiteLLM is a Python SDK and proxy server that provides a unified OpenAI-compatible interface to call over 100 large language model APIs from multiple providers, featuring consistent output, retry logic, budget controls, and extensive observability integrations.
Flowise is an open-source drag-and-drop platform that enables users to easily build and deploy customized Large Language Model (LLM) application workflows with a user-friendly interface and flexible deployment options.
Parlant is a Conversation Modeling engine that enables precise, consistent, and reliable control over GenAI-driven conversational agents by enforcing structured behavioral guidelines and adapting dynamically to user interactions.
ToolBench is an open platform for training, serving, and evaluating large language models with advanced tool-use capabilities using a large-scale, richly annotated dataset of real-world APIs.
RivetKit is a stateful serverless framework that enables building scalable, real-time, and collaborative applications deployable across multiple platforms including Rivet, Cloudflare Workers, Bun, and Node.js.
LlamaDeploy is an async-first framework that enables seamless deployment, scaling, and productionization of agentic multi-service workflows built with llama_index, facilitating easy transition from development to cloud-based production environments.
Ragbits is a modular framework providing building blocks for rapid development, deployment, and monitoring of scalable and reliable Generative AI applications with flexible LLM integration and advanced document processing capabilities.
Strands Agents Tools is a versatile toolkit that equips AI agents with powerful capabilities for file operations, system interaction, API communication, multimedia processing, memory management, and advanced reasoning to build intelligent applications efficiently.