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
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,...
Haystack is an AI orchestration framework for building customizable, production-ready NLP applications using large language models, vector search, and advanced retrieval techniques.
AI agent skill for generating polished HTML slide decks with various design styles, image prompts, social covers, and a WebGL/low-power presentation runtime.
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...
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.
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 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.
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.
Julep is a serverless platform that enables data and machine learning teams to build and orchestrate sophisticated AI workflows with smart memory, parallel processing, and seamless integration capabilities, all without managing infrastructure.
TaskWeaver is a code-first agent framework by Microsoft designed for planning and executing complex data analytics tasks through coordinated plugins and stateful code execution.
Embabel Agent Framework is a JVM-based framework for authoring dynamic agentic flows that combine LLM interactions with code and domain models, featuring sophisticated AI planning and extensibility.
FEDML is a unified and scalable machine learning library integrated with TensorOpera AI, enabling large-scale distributed training, model serving, and federated learning across diverse GPU cloud and edge environments.
OmAgent is a Python library that enables easy building of multimodal language agents with support for complex workflows, multimodal inputs, advanced reasoning algorithms, and local model deployment for rapid prototyping and production.
Datapizza AI is a fast, API-first Python framework for building reliable, observable, and vendor-agnostic generative AI solutions with multi-provider support and composable tools.
GenAI Processors is a lightweight Python library for building modular, asynchronous, and composable AI pipelines that enable efficient and parallel content processing for generative AI applications.
LLMCompiler is a framework that optimizes parallel function calling in large language models to improve latency, cost, and accuracy by automatically orchestrating task execution.
Jido is an autonomous agent framework for Elixir that enables building distributed, adaptive agent systems with composable workflows, real-time monitoring, and robust testing tools.
Python library from IBM Research for writing generative programs, where typed functions become structured LLM calls with schema-enforced output, natural-language requirements and automatic repair.
OctoTools is an open-source agentic framework with extensible tools designed for complex reasoning across diverse domains, supporting multiple LLM engines and achieving significant accuracy improvements over existing solutions.
Dynamiq is an orchestration framework for building and managing agentic AI and large language model applications, enabling complex multi-agent workflows and AI-powered solutions.
Autonomous engineering team runtime on AgentField: one API call spins up planner, architect, coder, reviewer and QA agents that scope, build, test and ship code across one or many repositories.
ActiveWorkflow is a platform that enables creating, scheduling, and monitoring polyglot workflows using agents in any programming language, facilitating business logic execution, resource polling, and event-driven orchestration without vendor lock-in.
Open-source AI app builder in Next.js where a chat agent writes and runs code inside sandboxed cloud VMs, with live preview, terminal, git-backed projects and one-click publishing.
FastAgency is an open-source framework that enables developers to quickly and efficiently deploy multi-agent AI workflows from prototype to production with unified interfaces, API integration, and scalable distributed system support.
Rill Flow is a high-performance, scalable distributed workflow orchestration engine designed for managing complex distributed workloads and integrating large language model services efficiently.
A curated and comprehensive repository of references and resources on Azure OpenAI services and Large Language Models, covering topics from RAG and agent frameworks to prompting, fine-tuning, and LLM applications.
Agentsflow is a web-based drag-and-drop platform for creating, connecting, and running autonomous AI agents using the autogen framework, designed for both beginners and advanced users.
syftr is an agent optimizer that uses multi-objective Bayesian Optimization and a novel Pareto Pruner to find the best agentic workflows balancing accuracy and competing objectives like cost and latency for a given budget.
aiFlows is a modular and collaborative AI workflow framework that enables concurrent execution and peer-to-peer distributed collaboration through reusable and customizable computational building blocks called Flows.
Enact is a Python framework for building, tracking, and improving generative software that integrates with machine learning models and APIs, offering features like recursive execution tracking, rewind/replay, and human-in-the-loop input sampling.