Stars
🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming
[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"
MiniCPM-V 4.5: A GPT-4o Level MLLM for Single Image, Multi Image and High-FPS Video Understanding on Your Phone
微舆：人人可用的多Agent舆情分析助手，打破信息茧房，还原舆情原貌，预测未来走向，辅助决策！从0实现，不依赖任何框架。
Hierarchical Reasoning Model Official Release
[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer
"DeepCode: Open Agentic Coding (Paper2Code & Text2Web & Text2Backend)"
Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation
An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.
Deep Learning and Reinforcement Learning Library for Scientists and Engineers
Mobile-Agent: The Powerful GUI Agent Family
A lightweight LMM-based Document Parsing Model
A True Instrumentable Binary Emulation Framework
Klavis AI (YC X25): MCP integration platforms that let AI agents use tools reliably at any scale
The open source platform for AI-native application development.
cube studio开源云原生一站式机器学习/深度学习/大模型AI平台，mlops算法链路全流程，算力租赁平台，notebook在线开发，拖拉拽任务流pipeline编排，多机多卡分布式训练，超参搜索，推理服务VGPU虚拟化，边缘计算，标注平台自动化标注，deepseek等大模型sft微调/奖励模型/强化学习训练，vllm/ollama/mindie大模型多机推理，私有知识库，AI模型市场…
[ECCV 2024] Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance
This Inventory management system is the currently Ford Asia Pacific after-sales logistics warehousing supply chain process . After I leave Ford , I start this project . You can share your vacant wa…
Recommendation Algorithm大规模推荐算法库，包含推荐系统经典及最新算法LR、Wide&Deep、DSSM、TDM、MIND、Word2Vec、Bert4Rec、DeepWalk、SSR、AITM，DSIN，SIGN，IPREC、GRU4Rec、Youtube_dnn、NCF、GNN、FM、FFM、DeepFM、DCN、DIN、DIEN、DLRM、MMOE、PLE、ESM…
FEDML - The unified and scalable ML library for large-scale distributed training, model serving, and federated learning. FEDML Launch, a cross-cloud scheduler, further enables running any AI jobs o…
Nexent is a zero-code platform for auto-generating agents — no orchestration, no complex drag-and-drop required. Nexent also offers powerful capabilities for agent running control, data processing …
[ICLR 2025] Hallo2: Long-Duration and High-Resolution Audio-driven Portrait Image Animation
OpenDILab Decision AI Engine. The Most Comprehensive Reinforcement Learning Framework B.P.
The next generation deep reinforcement learning tookit
open-source multimodal large language model that can hear, talk while thinking. Featuring real-time end-to-end speech input and streaming audio output conversational capabilities.
🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.
One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks