Awesome AI Agents › Stateful Serverless Frameworks
The project 'any-agent' by mozilla-ai is a Python library designed to provide a unified interface to access multiple different agent frameworks. It aims to simplify the process of switching between various agent frameworks by abstracting away the differences in their underlying APIs. This allows developers to work with different agentic frameworks without needing to adapt their code to each framework's specific API. The library supports several popular agent frameworks including Google ADK, LangChain, LlamaIndex, OpenAI Agents, Smolagents, and Agno AI, with plans to support more such as AWS Bedrock Agents, Pydantic AI, Microsoft AutoGen, and Crew AI. 'any-agent' also includes a 'trace-first' evaluation tool powered by large language models (LLM) that acts as a judge to flexibly evaluate agent execution traces. This feature enhances the ability to assess and improve agent performance. The library supports the use of Model Context Protocol (MCP) servers and allows the use of any LLM and provider compatible with LiteLLM syntax, provided the agent framework supports it. The project offers easy installation options, including the ability to install all supported frameworks at once. It provides a consistent API for defining and running both single and multi-agent systems, with support for tools integration such as web search and webpage visiting. The library is designed to be extensible, encouraging contributions to support new agent frameworks and additional features. Documentation, testing, and linting are integrated into the project, ensuring code quality and usability. The project also addresses practical usage scenarios such as running in Jupyter Notebooks, providing solutions to common issues like event loop conflicts. Overall, 'any-agent' serves as an abstraction layer that facilitates the use of multiple agent frameworks through a single, coherent interface, making it easier for developers to experiment with and deploy AI agents across different platforms.
https://github.com/mozilla-ai/any-agent
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.