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
microsoft/TaskWeaver
TaskWeaver is a sophisticated code-first agent framework developed by Microsoft designed to seamlessly plan and execute data analytics tasks. It stands out by interpreting user requests through code snippets and coordinating various plugins, implemented as functions, to perform data analytics in a stateful manner. Unlike many agent frameworks that only track chat history in text form, TaskWeaver preserves both chat history and code execution history, including in-memory data, which significantly enhances its expressiveness and capability to handle complex data structures such as high-dimensional tabular data. The framework supports advanced features like task decomposition, progress tracking, and reflective execution, allowing the agent to reflect on and adjust the execution process dynamically. It supports rich data structures in Python, such as DataFrames, enabling users to work with complex data more naturally. TaskWeaver also allows users to encapsulate custom algorithms into plugins and orchestrate them, facilitating the incorporation of domain-specific knowledge to improve reliability. TaskWeaver ensures stateful execution of generated code for a consistent user experience and includes code verification to detect potential issues before execution, providing suggestions for fixes. It is designed with security considerations, including session management to keep user data separate and isolated code execution processes to prevent interference. The framework is user-friendly, offering sample plugins, examples, tutorials, and detailed logs for easy debugging and understanding of the entire process, including LLM prompts, code generation, and execution. It supports extension to handle more complex tasks involving multiple agents and roles. Recent updates include support for vision input, enhanced reasoning capabilities, integration with observability tools, shared memory for inter-role communication, and optimization for local language models. TaskWeaver is open-source under the MIT license and encourages community contributions to enhance features such as UX/UI, prompt template management, plugin experience, asynchronous LLM interaction, and remote code execution support. It requires Python 3.10 or higher and offers an all-in-one Docker image for easy deployment.
https://github.com/microsoft/TaskWeaver
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.