"AutoAgent: Fully-Automated and Zero-Code LLM Agent Framework"

A curated list of resources on graph-based retrieval-augmented generation (GraphRAG) for customized large language models.

Uncommon Objects in 3D dataset

A curated list of papers, code and resources pertaining to image composition/compositing or object insertion/addition/compositing, which aims to generate realistic composite image.

Align Anything: Training All-modality Model with Feedback

Hallo3: Highly Dynamic and Realistic Portrait Image Animation with Diffusion Transformer Networks

A highly optimized LLM inference acceleration engine for Llama and its variants.

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。

Manuscript is a revolutionary blockchain data streaming framework. With Manuscript, you can seamlessly integrate on-chain and off-chain data into target data storage for unrestricted querying and a…

以开源为核心的IDaas/IAM平台，用于管理企业内员工账号、权限、身份认证、应用访问，帮助整合部署在本地或云端的内部办公系统、业务系统及三方 SaaS 系统的所有身份，实现一个账号打通所有应用的服务。

Lyra: An Efficient and Speech-Centric Framework for Omni-Cognition

数据标注是一款专门对文本数据进行处理和标注的工具，通过简化快捷的文本标注流程和动态的算法反馈，支持用户快速标注关键词并能通过算法持续减少人工标注的成本和时间。数据标注的过程先由人工标注构筑基础，再由自动标注反哺人工标注，最后由人工标注进行纠偏，从而大幅度提高标注的精准度和高效性。数据标注是一个完全开源的项目，无商业版，但是需要依赖开源的数字底座进行人员岗位管控。各类词库结果会定期在本平台公开。

AML end to end system

工作流引擎对内提供单位/机关流程管理规则和内部业务流程的数字化落地实践；对外提供自动化地第三方业务驱动、接口接入和算法单元驱动能力。工作流引擎在提供底层驱动引擎的同时对全局透明监控、安全防御和国产化特色功能进行充分考虑，是内部流程管理和业务算法驱动的不二之选。

"LightRAG: Simple and Fast Retrieval-Augmented Generation"

One-stop data intelligence agent, providing insights from all mainstream data formats in a single dialogue box, including documents, databases, business systems, and images.一站式数据智能体，一个对话框提供所有主流格式数据…

The Official Implementation of PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling

The "virtual_human_stream" project is a real-time digital human system supporting audio-video dialogue. It integrates models like ernerf, musetalk, and wav2lip for voice cloning, video stitching, a…

Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities。

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

The first open autoregressive foundational video AI model.

A high-performance IM server.

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

Dynamic PDB datasets

Nexa SDK is a comprehensive toolkit for supporting ONNX and GGML models. It supports text generation, image generation, vision-language models (VLM), auto-speech-recognition (ASR), and text-to-spee…

Awesome LLMs on Device: A Comprehensive Survey

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.

https://freechat.fun