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
agentic-ai/enact
Enact is a Python framework designed for building generative software that integrates with machine learning models or APIs generating distributions of outputs. It focuses on providing core functionalities essential for developing, inspecting, and improving software that samples from generative subsystems such as large language models (LLMs) and diffusion models. The framework enables recursive tracking of generative executions, persistence of execution data and system parameters in versioned storage, exploration of possible system executions through rewind and replay, and transformation of existing code into asynchronous flows that can pause and sample input from external systems or users. Enact supports orchestrating higher-order generative flows where AI systems can write and run software, offering a first-principles approach close to the programming language level. This makes it distinct from libraries that focus on unified integrations or specific algorithm schemas for generative flows. Key features include invocation tracking, rewind/replay capabilities, human-in-the-loop input sampling treated as generative distributions, and versioning of components through structural hashing. The framework supports both synchronous and asynchronous Python programs, allowing partial executions to be persisted and resumed later or on different machines. Enact also facilitates making custom types compatible with the framework by defining them as resources or wrappers. It is available as a PyPI package and comes with examples demonstrating its capabilities, such as a generic Monte Carlo Tree Search implementation exploring execution trees of scaffolding programs. Overall, Enact aims to empower developers to build sophisticated generative software with enhanced control, inspection, and iterative improvement capabilities.
https://github.com/agentic-ai/enact
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.