Awesome AI Agents › Stateful Serverless Frameworks
Chipper is an innovative AI interface designed for tinkerers and developers who want to build and customize Retrieval-Augmented Generation (RAG) pipelines and workflows. It offers a modular, hackable, and lightweight architecture that supports document splitting, web scraping, and query workflows to enhance generative AI models with advanced information retrieval capabilities. The project provides both a web interface and a command-line interface (CLI), making it accessible for different user preferences. Chipper integrates with several powerful tools and platforms including Ollama, Haystack, Hugging Face, Docker, TailwindCSS, and ElasticSearch, running as a fully containerized service for easy deployment. Originally created as a personal tool to assist with book writing by leveraging local RAG and large language models (LLMs) while maintaining privacy and avoiding cloud services, Chipper has evolved into a fully extensible and dockerized service. It supports local and cloud model usage, allowing users to run models locally with Ollama or connect to remote models via the Hugging Face API. The system efficiently stores and retrieves vectorized data using ElasticSearch and processes documents by chunking them into structured segments. Additional features include web scraping for content extraction, audio transcription, and an offline-capable web UI built with vanilla JavaScript and TailwindCSS. Chipper also functions as a proxy for the Ollama API, enabling interoperability with third-party clients like Enchanted and Open WebUI, and extends Ollama with retrieval capabilities. It supports API security through API key and Bearer token authentication and offers distributed processing by chaining multiple Chipper instances for workload distribution. The project emphasizes education and exploration, aiming to be approachable for beginners while providing a robust platform for experts to experiment and innovate. It is not intended for commercial or production use without due diligence. Overall, Chipper is a versatile and user-friendly platform for building and experimenting with AI-powered RAG workflows, combining local and cloud AI models with advanced data processing and retrieval features in a containerized environment.
https://github.com/TilmanGriesel/chipper
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.