An open-source AI application building framework for full-stack apps, providing a unified SDK and developer toolchain.

Model & Inference FrameworkLarge Language ModelsSDK

VIEW DETAILS →

An AI Agent platform that automates browser workflows using Vision LLMs, extending Playwright with natural language commands for web automation, workflow orchestration, and structured data extraction.

Model & Inference FrameworkMultimodalAI Agents

VIEW DETAILS →

A local-first agentic framework acting as a personal operating system, leveraging file intelligence, event-driven workflow automation, and LLMs for cross-modal task execution and multi-platform interaction.

OtherMultimodalRAG

VIEW DETAILS →

macOS GUI automation tool powered by AI vision — captures screenshots, detects UI elements via multi-provider LLMs, and executes clicks/types/scrolls through natural language or scripted workflows

Model & Inference FrameworkMultimodalModel Context Protocol

VIEW DETAILS →

An open-source Python framework for real-time voice and multimodal conversational AI agents, enabling end-to-end streaming voice interaction via composable Pipeline architecture.

MultimodalMulti-Agent SystemAI Agents

VIEW DETAILS →

The first open-source, agentic video production system with 12 structured pipelines and 52 production tools, enabling end-to-end video creation via natural language inside AI coding assistants.

Natural Language ProcessingMultimodalAI Agents

VIEW DETAILS →

A self-hosted AI chat platform that unifies major AI providers into a single, privacy-focused interface.

MultimodalRAGModel Context Protocol

VIEW DETAILS →

A local-first personal AI assistant achieving full data sovereignty and privacy protection through a LangGraph ReAct agent and personal knowledge graph, with all inference running locally via Ollama by default.

Model & Inference FrameworkMultimodalModel Context Protocol

VIEW DETAILS →

A local AI inference engine for Apple Silicon with OpenAI-compatible API, supporting multi-modal, tool calling, and smart cloud routing.

AI AgentsLarge Language ModelsModel Context Protocol

VIEW DETAILS →

Open-source digital human agent platform that creates real-time video-callable AI agents from a single photo, with RAG knowledge import, voice cloning, and modular plugin architecture.

Docs, Tutorials & ResourcesMultimodalRAG

VIEW DETAILS →