Awesome AI AgentsStateful Serverless Frameworks

rivet-gg/rivetkit

⭐ 4620 TypeScript added to this list on 2025-06-16 repository created 2024-02-07

RivetKit, also known as ActorCore, is a stateful serverless computing framework designed to run anywhere, enabling developers to build stateful, AI agent, collaborative, and local-first applications with ease. It supports deployment across multiple platforms including Rivet, Cloudflare Workers, Bun, Node.js, and more, providing flexibility and scalability without the need to manage servers. The core concept of RivetKit is to offer long-lived, stateful compute units that behave like tiny servers retaining state between requests, unlike traditional serverless functions that are stateless and have timeouts. This allows applications to maintain memory and state seamlessly, improving performance and user experience. RivetKit eliminates the need for external databases or ORMs by automatically saving the code's state using regular JavaScript objects or SQLite (with SQLite support planned for release). This approach ensures blazing-fast reads and writes since the state is stored on the same machine as the compute, avoiding latency spikes and database round trips. The framework also simplifies real-time updates and broadcasting of state changes without relying on external pub/sub systems or polling, enabling low-latency event-driven applications. Designed to run on the edge, RivetKit stores data close to users, ensuring instant interactions and responsiveness. It supports serverless and scalable architecture, automatically scaling with usage and running code on-demand. The project provides extensive examples and snippets for various use cases such as chat rooms, AI agents, local-first sync, per-tenant SaaS, collaborative documents, multiplayer games, and rate limiters, demonstrating its versatility. RivetKit integrates with popular frameworks like React and supports multiple programming languages including JavaScript, TypeScript, Python, and Rust. It also offers compatibility with various storage backends like Redis, Postgres, file systems, and in-memory storage. The project encourages community contributions and provides documentation, Discord support, and social media channels for engagement. Overall, RivetKit is a powerful and flexible framework for building modern, stateful, and real-time applications that can run seamlessly across diverse environments and infrastructures, making it an excellent choice for developers looking to leverage serverless computing with persistent state and real-time capabilities.

https://github.com/rivet-gg/rivetkit

actoractorsagentsaiai-agentai-agent-exampleai-agentsbunbunjschat-roomcloudflare-durable-objectscloudflare-workerscollaborative-applicationscollaborative-documentdurable-objectsdurable-stateedge-computingfast-reads-and-writesfile-systemjavascriptjavascript-objectslocal-first-applicationslocal-first-synclong-lived-computelow-latency-eventsmemory-storagemultiplayer-gameno-databasenode.jsnodejsper-tenant-saasper-user-databasespostgrespythonrate-limiterreact-integrationrealtime-updatesredisrivetrustscalableserverlesssqlitestateful-serverlessstream-processingsupabasetypescriptvercelyjs-crdt

Also in Stateful Serverless Frameworks

BerriAI/litellm

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.

FlowiseAI/Flowise

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.

emcie-co/parlant

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.

OpenBMB/ToolBench

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.

run-llama/llama_deploy

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.

deepsense-ai/ragbits

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/mirascope

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.

strands-agents/tools

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.