Stars
MiroThinker is an open source deep research agent optimized for research and prediction. It achieves a 60.2% Avg@8 score on the challenging GAIA benchmark.
The ECShopX Open Source E-Commerce System is free for commercial use, subject to the Apache 2.0 License and Shopex’s additional terms.
JittorGeometric is a Jittor-based graph machine learning library.
Fully emulating the RISC-V Base Integer Instruction Set (WIP)
Auto-Manage Your Personal Task Context with AI.
Code for "FaithLens: Detecting and Explaining Faithfulness Hallucination"
A sophisticated LangGraph-based agent that automates financial options analysis with real-time data from Polygon.io, smart caching, persistent memory, and professional-grade analysis. Built for tra…
GigaBrain-0: A World Model-Powered Vision-Language-Action Model
Reward Forcing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillation
HunyuanVideo-1.5: A leading lightweight video generation model
TeleMem is a high-performance drop-in replacement for Mem0, featuring semantic deduplication, long-term dialogue memory, and multimodal video reasoning.
GigaModels: A Comprehensive Repository and Platform for Multi-modal, Generative, and Perceptual Models
GigaWorld-0: World Models as Data Engine to Empower Embodied AI
SAG - SQL驱动的RAG引擎 · 查询时自动构建知识图谱 | SQL-Driven RAG Engine · Automatically Build Knowledge Graph During Querying
A lightweight browser-to-NAS pipeline for capturing and downloading web videos. It integrates a Chrome Extension with a NAS-hosted Docker backend (FastAPI, workers, FFmpeg) to automatically detect,…
DeepThinkVLA: Enhancing Reasoning Capability of Vision-Language-Action Models
World's most powerful open data catalog for building a high-performance, geo-distributed and federated metadata lake.
Fulling is an AI-powered Full-stack Engineer Agent. Built with Next.js, Claude, shadcn/ui, and PostgreSQL. Use kubernetes as infra.
🔥 The first open-sourced diffusion vision-langauge-action model.
[NeurIPS 2025] Codes for paper Foundation Cures Personalization: Improving Personalized Models' Prompt Consistency via Hidden Foundation Knowledge
Implementation of "YOLOv13: Real-Time Object Detection with Hypergraph-Enhanced Adaptive Visual Perception".
A transparent, minimal, and hackable agent framework. ~300 lines of readable code. Full control, no magic.
A cross-platform instant messaging client application built with Tauri and Vue 3, featuring one-to-one chat, group chat, file transfer, audio/video calling, screen recording, screenshot capture, an…
UCCL is an efficient communication library for GPUs, covering collectives, P2P (e.g., KV cache transfer, RL weight transfer), and EP (e.g., GPU-driven)