A Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎，预测万物

HunyuanVideo-1.5: A leading lightweight video generation model

Mirix is a multi-agent personal assistant designed to track on-screen activities and answer user questions intelligently. By capturing real-time visual data and consolidating it into structured mem…

High-performance inference framework for large language models, focusing on efficiency, flexibility, and availability.

MemoryBear Equip AI with human-like memory capability

🔬 Harness Vibe Research with Self-evolving AI Scientists

14-stage Fusion Pipeline for LLM token compression — reversible compression, AST-aware code analysis, intelligent content routing. Zero LLM inference cost. MIT licensed.

JoyAI-Image is the unified multimodal foundation model for image understanding, text-to-image generation, and instruction-guided image editing.

[CVPR 2026] Towards Real-Time Diffusion-Based Streaming Video Super-Resolution — An efficient one-step diffusion framework for streaming VSR with locality-constrained sparse attention and a tiny co…

Multi-Agent System Framework For Complex Tasks

Official inference code for SoulX-LiveAct: Towards Hour-Scale Real-Time Human Animation with Neighbor Forcing and ConvKV Memory

OpenClaw Security Vault — Atomic "claw" control: every AI reach, within your sight.

One dashboard. An entire research team.

Dynamic MBTI Personality Simulation for LLM Agents via Carl Jung's Theory. A framework that enables LLM agents' MBTI personalities to naturally evolve and grow through interaction.

Life Agent RU YEE — An AI-powered life management agent that autonomously handles daily routines including meal planning, grocery shopping, schedule coordination, and household task automation via …

🦞+🔬: NanoResearch: The Autonomous AI Research Assistant

Key-Value Store Solution for AI

Give your AI agent a brain that remembers. Local memory system for Claude Code — 100% private, GPU-accelerated, zero cloud dependency.

Spiking Neural Network library built natively on Apple MLX

🔥🔥🔥[AAAI 2026 Oral] Official Implementation of Robust-R1: Degradation-Aware Reasoning for Robust Visual Understanding

A light implementation of megatron for research and study

Multi-model DAG-driven parallel AI film generation — parallel speedup scales with scene independence; Generate film scenes simultaneously instead of one by one; "把影视生成的执行图从拓扑序变成关键路径最优调度" ; 唯一把场景叙事依…

Official code for world model Kairos 3.0

MathClaw is a multimodal learning assistant designed for middle and high school mathematics.

Let AI think and express like you. This framework provides a complete assembly line: from the noise processing of original chat records, to the seamless switching of multi-model adaptation layers, …

GPU-accelerated NeuroEvolution of Augmenting Topologies (NEAT)

🧠 AI-powered Personalized Exam System: Integrating OpenPangu LLM, Knowledge Graph RAG, and BKT algorithm for adaptive question generation and recommendation. 基于LLM与知识图谱的智能个性化出题系统。

Personalized paper recommendation for OpenClaw / Feishu, powered by AMiner + arXiv + LLMs.

Cheers: Decoupling Patch Details from Semantic Representations Enables Unified Multimodal Comprehension and Generation

MetaDE is a GPU-accelerated evolutionary framework that optimizes Differential Evolution (DE) strategies via meta-level evolution. Supporting both JAX and PyTorch, it dynamically adapts mutation an…