Awesome AI Agents › Stateful Serverless Frameworks
BeeAI is an open platform designed to facilitate the discovery, execution, and composition of AI agents from any framework or programming language. It enables users to integrate AI agents seamlessly regardless of the underlying technology, making it framework-agnostic. The platform supports building complex workflows by composing multiple AI agents, allowing for sophisticated multi-agent orchestration from simple building blocks. BeeAI provides a powerful agent catalog with integrated search capabilities, making it easy to explore and find existing AI agents. The platform offers first-class support for Python and TypeScript developers through the BeeAI Framework, enhancing the development experience for these languages. Users can quickly get started with BeeAI by installing it via Homebrew or other methods, configuring their preferred large language model (LLM) provider, and launching a web interface for interaction. The platform also supports command-line usage, enabling users to list available agents, run chat agents, and compose agents in sequential workflows directly from the terminal. Comprehensive documentation is available at docs.beeai.dev, and a reference library of agent implementations can be found at beeai.dev/agents. The BeeAI community is active on GitHub Discussions and Discord, providing support, idea exchange, and collaboration opportunities. The project encourages contributions and follows a code of conduct to maintain a respectful and productive community environment. BeeAI is developed as part of the Linux Foundation AI & Data program, emphasizing open, collaborative, and community-driven development. It draws inspiration from notable projects such as the Model Context Protocol, Language Server Protocol, JSON-RPC, and the Natural Language Interaction Protocol. Overall, BeeAI aims to simplify the integration and orchestration of AI agents across diverse frameworks, fostering innovation and ease of use in AI agent deployment and management.
https://github.com/i-am-bee/beeai-platform
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.
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.