Awesome AI Agents › Stateful Serverless Frameworks
The django-ai-assistant project is designed to integrate AI Assistants with the Django web framework, enabling developers to build intelligent applications that leverage the power of large language models (LLMs). This integration allows AI Assistants to interact with Django's backend by calling methods and performing tasks that users require, effectively combining AI capabilities with Django's productivity and robustness. The project supports advanced AI features such as AI Tool Calling and Retrieval-Augmented Generation (RAG), which facilitate the creation of state-of-the-art AI Assistants within Django applications. These features enable the AI to access external tools and retrieve relevant information dynamically, enhancing the assistant's ability to provide accurate and context-aware responses. django-ai-assistant is well-documented, with comprehensive guides and examples available on its official documentation site. The project also offers a quick 5-minute demo video to help users get started rapidly. It fosters a community environment through a dedicated Discord server where users can ask questions, share their projects, and collaborate. The project encourages contributions from the community, inviting developers to address existing issues or propose new ideas via GitHub discussions. It provides a contributing guide to assist developers in setting up the development environment and submitting pull requests. Maintained by Vinta Software, django-ai-assistant is an open-source initiative with options for commercial support. Vinta Software offers professional assistance for organizations seeking expert help with the project. Overall, django-ai-assistant is a powerful tool for developers looking to enhance their Django applications with intelligent AI-driven features, making it easier to build sophisticated, interactive, and responsive web applications.
https://github.com/vintasoftware/django-ai-assistant
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.