nexu-io/open-design
Open Design is a local-first, open-source desktop application that serves as an alternative to Claude Design, integrating with various coding agents to generate web, desktop, and mobile prototypes,...
Awesome AI Agents › Generative Software Frameworks
google-gemini/genai-processors
GenAI Processors is a lightweight Python library designed to facilitate efficient and parallel content processing, particularly for generative AI applications. The core concept of the library is the 'Processor', which represents a unit of work that processes streams of data parts, such as text or images, asynchronously. This design allows for modular, asynchronous, and composable AI pipelines that can handle complex workflows with ease. The library supports breaking down complex tasks into reusable components called 'Processor' and 'PartProcessor' units. These units can be chained or parallelized to create sophisticated data flows and agentic behaviors. It integrates seamlessly with the GenAI API, providing ready-to-use processors like 'GenaiModel' for turn-based API calls and 'LiveProcessor' for real-time streaming interactions. GenAI Processors is highly extensible, allowing users to create custom processors by inheriting from base classes or using simple function decorators. It supports rich content handling, including various content types such as text, images, audio, and custom JSON, wrapped in a 'ProcessorPart' that carries metadata like MIME type and role. Built on Python's asyncio framework, the library orchestrates concurrent tasks efficiently, including network I/O and compute-heavy subthreads. It also offers utilities for managing asynchronous streams, such as splitting, concatenating, and merging streams of 'ProcessorPart's. The project provides comprehensive documentation and examples, including colabs for beginners and advanced users, demonstrating how to create processors, work with live APIs, and build real-time agents. It is open for community contributions and is licensed under the Apache License 2.0. Overall, GenAI Processors is a powerful tool for developers looking to build modular, scalable, and efficient AI content processing pipelines with support for real-time and turn-based generative AI workflows.
https://github.com/google-gemini/genai-processors
Also in Generative Software Frameworks
deepset-ai/haystack
Haystack is an AI orchestration framework for building customizable, production-ready NLP applications using large language models, vector search, and advanced retrieval techniques.
op7418/guizang-ppt-skill
AI agent skill for generating polished HTML slide decks with various design styles, image prompts, social covers, and a WebGL/low-power presentation runtime.
HKUDS/Agentic-AIGC
ViMax is an agentic AI system for end-to-end video generation, transforming raw ideas, novels, or scripts into complete video content by orchestrating scriptwriting, storyboarding, character creati...
The-Pocket/PocketFlow
Pocket Flow is a minimalist 100-line LLM framework that uses a graph-based abstraction to enable expressive multi-agent systems, workflows, and retrieval-augmented generation, designed for high productivity and minimal bloat.
Netflix/metaflow
Metaflow is a human-centric framework by Netflix that streamlines building, managing, and deploying real-life AI and machine learning systems from prototyping to production at scale.
presenton/presenton
Presenton is an open-source AI-powered presentation generator and API that runs locally, offering customizable layouts, multiple AI model integrations, versatile image generation, and privacy-focused presentation creation and export.
thesysdev/openui
OpenUI is a full-stack Generative UI framework that offers a compact, streaming-first language for model-generated UI, a React runtime, and token-efficient chat interfaces.