Codebase for Iterative DPO Using Rule-based Rewards

Build multimodal language agents for fast prototype and production

数据流引擎是一款面向数据集成、数据同步、数据交换、数据共享、任务配置、任务调度的底层数据驱动引擎。数据流引擎采用管执分离、多流层、插件库等体系应对大规模数据任务、数据高频上报、数据高频采集、异构数据兼容的实际数据问题。

Open-Tax is an AI-powered cloud platform transforming tax compliance through automated data integration, real-time anomaly detection, and multi-jurisdictional reconciliation.

Eko (Eko Keeps Operating) - Build Production-ready Agentic Workflow with Natural Language - eko.fellou.ai

[NeurIPS 2024 Datasets and Benchmarks Track] Closed-Loop E2E-AD Benchmark Enhanced by World Model RL Expert

Run AI models end-to-end encrypted.

Secure storage system based on cryptography｜基于密码学的安全存储系统

LLM-FuzzX is a user-friendly fuzz testing tool for Large Language Models (e.g., GPT, Claude, LLaMA), featuring advanced task-aware mutation strategies, fine-grained evaluations, and jailbreak detec…

Re-movery

Allegro is a powerful text-to-video model that generates high-quality videos up to 6 seconds at 15 FPS and 720p resolution from simple text input.

"LightRAG: Simple and Fast Retrieval-Augmented Generation"

TEN Agent is a conversational AI powered by the TEN, integrating Gemini 2.0 Live, OpenAI Realtime, RTC, and more. It delivers real-time capabilities to see, hear, and speak, while being fully compa…

Cocos simplifies game creation and distribution with Cocos Creator, a free, open-source, cross-platform game engine. Empowering millions of developers to create high-performance, engaging 2D/3D gam…

A Doctor for your data

A multi-modal vector database that supports upserts and vector queries using unified SQL (MySQL-Compatible) on structured and unstructured data, while meeting the requirements of high concurrency a…

The first open autoregressive foundational video AI model.

Hallo2: Long-Duration and High-Resolution Audio-driven Portrait Image Animation

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 (…

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。

网络硬盘是通过存储、分类、检索、分享、协作、下发、回收、展示等方式管理文档、文件、图片、音频、视频等资料的工具。网络硬盘擅长在国产的私有化环境中管控文档权限、存储空间分配、安全加密、链接分享，同时支持一定轻量级的文件任务收发。网络硬盘需要依赖开源的数字底座进行人员岗位管控。

cube studio开源云原生一站式机器学习/深度学习/大模型AI平台，支持sso登录，大数据平台对接，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，边缘计算，标注平台，自动化标注，大模型微调，vllm大模型推理，llmops，私有知识库，AI模型应用商店，支持模型一键开发/推理/微调，支持国产cpu/gpu/npu芯片，支持R…

MiniCPM3-4B: An edge-side LLM that surpasses GPT-3.5-Turbo.

Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance

Orillusion is a pure Web3D rendering engine which is fully developed based on the WebGPU standard.