On-device full-stack AI SDK for Flutter with LLM, Vision, Speech, Image Gen, and RAG; features compute budget contracts and adaptive QoS with zero cloud dependency.

大语言模型MultimodalSDK

VIEW DETAILS →

A four-service collaborative AI desktop assistant framework with streaming tool calling, GRAG knowledge graph memory, Live2D avatar, and voice interaction

RAGMultimodalAI Agents

VIEW DETAILS →

A local-first AI desktop application integrating conversational AI, visual generation, vector search, and multi-channel connectivity, featuring deep research modes and local knowledge bases.

MultimodalModel Context ProtocolRAG

VIEW DETAILS →

A learnable, configurable, and pluggable Omni-Avatar Assistant framework built on LiveKit, featuring real-time interaction, multimodal memory, user persona, and external tool integration.

Docs, Tutorials & ResourcesRAGMultimodal

VIEW DETAILS →

Odyssey is a framework that empowers LLM-based Minecraft agents with open-world skills, featuring 40 primitive skills and 183 compositional skills, enabling AI to autonomously explore, learn, and execute diverse tasks in the Minecraft universe.

Agent & ToolingPythonLangChain

VIEW DETAILS →

A customizable AI desktop companion project with character settings, voice conversations, long-term memory capabilities, and sub-1-second response times. Integrates with Live2D models for visual presentation.

Agent & ToolingPythonElectron

VIEW DETAILS →

A high-performance drop-in replacement for Mem0 featuring semantic deduplication, long-term dialogue memory, and multimodal video reasoning capabilities, specifically optimized for multi-character and long-term interaction scenarios.

Agent & ToolingPythonAI Agents

VIEW DETAILS →

A GPT-powered video retrieval and streaming agent that enables developers to upload multiple videos, search across content in real-time, generate summarized text answers through RAG, and publish searchable collections on the ChatGPT store.

Agent & ToolingPythonFlask

VIEW DETAILS →

An open-world multi-task agent system with memory-augmented multimodal language models that can understand visual observations and human instructions, generate sophisticated plans, and perform embodied control in the Minecraft universe, capable of completing over 200 diverse tasks with human-like control and observation.

Agent & ToolingPythonPyTorch

VIEW DETAILS →

LAYRA is an enterprise-ready, out-of-the-box solution that unlocks next-generation intelligent systems powered by visual RAG and limitless visual multi-step agent workflow orchestration. It sees documents like a human, preserves layout and graphical elements, and executes arbitrarily complex workflows with full Python control.

Agent & ToolingPythonTypeScript

VIEW DETAILS →