Awesome AI Agents › Stateful Serverless Frameworks
Flowise is an open-source project that provides a drag-and-drop user interface to build customized Large Language Model (LLM) application flows easily. It is designed to simplify the creation and deployment of LLM-powered applications by allowing users to visually design workflows without deep programming knowledge. The project consists of three main modules within a monorepository: a Node.js backend server that handles API logic, a React-based frontend UI for building and managing flows, and a components module that integrates third-party nodes for extended functionality. Additionally, it includes auto-generated API documentation using Swagger UI. Flowise supports quick installation and startup via Node.js and npm, with options for running the application locally or using Docker containers for easier deployment. It also supports authentication by enabling username and password protection for the app. The project is highly configurable through environment variables and supports various deployment platforms including AWS, Azure, Digital Ocean, Google Cloud Platform, Alibaba Cloud, and others, making it suitable for self-hosting in diverse infrastructure environments. The user interface is designed to be intuitive, featuring drag-and-drop capabilities to build complex LLM workflows visually. This lowers the barrier for developers and non-developers alike to create AI-driven applications. The project is actively maintained with a strong community presence on Discord and Twitter, and it encourages contributions from developers. Comprehensive documentation and guides are available to assist users in installation, development, and deployment. Flowise also offers a cloud-hosted version for users who prefer a managed service. The project is licensed under the Apache License Version 2.0, ensuring it remains free and open for modification and distribution. Overall, Flowise aims to democratize access to LLM technology by providing an accessible platform for building AI applications with minimal setup and coding effort.
https://github.com/FlowiseAI/Flowise
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.
CNCF runtime providing durable workflow execution, state, pub/sub and secure service-mesh primitives that AI agents and distributed applications call from any language via a sidecar.
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.
Mirascope is a flexible and user-friendly library that provides a unified interface to work with multiple large language model providers, simplifying AI-driven text generation and information extraction tasks.