Cordove's Stars
URSA-MATH/URSA-MATH
mind-network/mind-eliza-integration
Integration repo between Mind Network and eliza
wxai-space/LightAgent
**LightAgent** is an extremely lightweight active Agentic Framework with memory, tools , and a Tree of Thought (`ToT`). It supports swarm-like multi-agent collaboration, automated tool generation, and agent assessment, with underlying model support for OpenAI, ChatGLM, Baichuan, DeepSeek, Qwen
acharkq/NExT-Mol
Source code for ICLR2025 paper "NExT-Mol: 3D Diffusion Meets 1D Language Modeling for 3D Molecule Generation".
risesoft-y9/Digital-Infrastructure
数字底座是一款面向大型政府、企业数字化转型,基于身份认证、组织架构、岗位职务、应用系统、资源角色、数据目录、安全控制等功能构建的统一且安全的管理支撑平台。数字底座基于三员管理模式,具备微服务、多租户、容器化和国产化,支持用户利用代码生成器快速构建自己的业务应用,同时可关联诸多成熟且好用的内部生态应用。
kwuking/TimeMixer
[ICLR 2024] Official implementation of "TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting"
papersgpt/papersgpt-for-zotero
Zotero chat PDF with AI, DeepSeek, GPT 4.5, ChatGPT, Claude, Gemini
zhiyuancui/Creative-AIGC-Suite
AIGC Creative Suite
facebookresearch/uco3d
Uncommon Objects in 3D dataset
bird-bench/BIRD-CRITIC-1
BIRD-CRITIC 1.0: Can Large Language Models Solve USER SQL Issues in Real-World Database Applications?
HJYao00/Mulberry
Mulberry, an o1-like Reasoning and Reflection MLLM Implemented via Collective MCTS
GenjiYin/paper_reading_agent
论文阅读助手
NexaAI/nexa-sdk
Nexa SDK is a comprehensive toolkit for supporting GGML and ONNX models. It supports text generation, image generation, vision-language models (VLM), Audio Language Model, auto-speech-recognition (ASR), and text-to-speech (TTS) capabilities.
lakesoul-io/LakeSoul
LakeSoul is an end-to-end, realtime and cloud native Lakehouse framework with fast data ingestion, concurrent update and incremental data analytics on cloud storages for both BI and AI applications.
SSCT-Lab/QATest
nesaorg/nesa
Run AI models end-to-end encrypted.
826148267/cjml_server
Secure storage system based on cryptography|基于密码学的安全存储系统
heyangxu/Re-movery
Re-movery
HKUDS/LightRAG
"LightRAG: Simple and Fast Retrieval-Augmented Generation"
fudan-generative-vision/hallo2
Hallo2: Long-Duration and High-Resolution Audio-driven Portrait Image Animation
Everlyn-Labs/Everlyn-1
The first open autoregressive foundational video AI model.
Orillusion/orillusion
Orillusion is a pure Web3D rendering engine which is fully developed based on the WebGPU standard.
fudan-generative-vision/hallo
Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation
TaskingAI/TaskingAI
The open source platform for AI-native application development.
GoEdgeLab/EdgeAdmin
WuKongOpenSource/WukongCRM-11.0-JAVA
悟空CRM-基于Spring Cloud Alibaba微服务架构 +vue ElementUI的前后端分离CRM系统
ByConity/ByConity
ByConity is an open source cloud data warehouse
chaihahaha/dl-template
deep learning template code
oriyor/ret-robust
Implementation of the paper: "Making Retrieval-Augmented Language Models Robust to Irrelevant Context"
microsoft/UFO
A UI-Focused Agent for Windows OS Interaction.