Awesome AI Agents › Stateful Serverless Frameworks
Strands Agents Tools is a comprehensive toolkit designed to empower AI agents with a wide range of practical capabilities, bridging the gap between large language models and real-world applications. This project offers a model-driven approach that allows developers to build AI agents efficiently with minimal code. The toolkit includes a variety of tools that enable file operations such as reading, writing, and editing files with advanced features like syntax highlighting and intelligent modifications. It supports secure shell command execution, allowing agents to interact with the operating system and run scripts safely. Memory management is a key feature, with support for storing user and agent memories across sessions using Mem0 and Amazon Bedrock Knowledge Bases, enabling personalized user experiences. The HTTP client tool facilitates API interactions with comprehensive authentication support, while the Slack client enables real-time event handling and message processing within Slack. Python code execution is supported with state persistence and safety measures, allowing agents to run complex logic and data analysis. Mathematical tools provide advanced calculation and symbolic math capabilities. Integration with AWS services is seamless, enabling cloud resource management. The toolkit also includes image and video processing tools for generating and manipulating multimedia content, as well as audio output capabilities for speech generation. Environment management tools help handle configuration securely, and journaling features allow structured logging and documentation. Task scheduling with cron jobs, advanced reasoning tools for complex problem-solving, and swarm intelligence for coordinating multiple AI agents in parallel are also part of the toolkit. Additionally, the Batch Tool allows simultaneous execution of multiple tools. Installation is straightforward via pip, with options for quick or development installs. The project is actively maintained with detailed documentation, sample projects, and a Python SDK to facilitate integration. Overall, Strands Agents Tools provides a versatile and powerful set of functionalities that enable developers to create intelligent, interactive, and multi-capable AI agents for diverse applications.
https://github.com/strands-agents/tools
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.