dromara/wgai

开箱即用的JAVA AI 图片、视频语音识别&OCR平台AI合集包含旦不仅限于(车牌识别、安全帽识别、开门关门、常用类物识别等) 图片和视频识别 可自主 融合了AI图像识别opencv、yolo、ocr、esayAI内核识别;AI智能客服、AI语言模型、 无任何第三方API接口可定制化自主离线化部署并自主化行业化使用 避免占用内存、GPU消耗训练与识别分开使用;

What it solves

WGAI is a comprehensive AI management platform designed to provide an "out-of-the-box" solution for industrial-grade multimodal AI. It addresses the complexity of deploying and managing various AI capabilities—such as computer vision, speech recognition, and robotics navigation—within a single, offline-capable system.

How it works

The platform integrates multiple AI kernels, including OpenCV, YOLO, OCR, and ChatGPT, to provide a full-stack server architecture. It employs a decoupled architecture where training and recognition are separated to prevent excessive memory and GPU consumption, allowing for efficient offline deployment.

Who it’s for

It is primarily aimed at industrial users and developers who need a centralized platform for multimodal AI tasks, including those requiring offline deployment, real-time video analysis, and AGV (Automated Guided Vehicle) navigation.

Highlights

  • Multimodal Integration: Combines vision (YOLO, OpenCV, OCR, face recognition), audio (speech recognition), and text (ChatGPT) in one platform.
  • Industrial Robotics Support: Includes features for AGV automatic navigation, map scanning, path planning, and obstacle avoidance.
  • End-to-End Workflow: Supports online data labeling, model training, and real-time result evaluation.
  • Real-time Monitoring: Provides video analysis alerts, system resource monitoring (CPU/JVM/Redis), and alarm message subscriptions.

Related

  • Project
    open-webui/open-webui

    Open WebUI is an open‑source, self‑hosted web interface for LLMs that works with any OpenAI‑compatible API and with local Ollama models. It provides a rich UI (chat, notes, channels, calendar, voice/video, image generation), extensible plugin system, RBAC, multi‑model support, built‑in RAG (vector DBs, web search), an “Open Terminal” for agents to run code, and enterprise features like LDAP/SSO, SCIM provisioning, and observability. Install via pip, Docker (CPU/GPU, bundled Ollama), or Kubernetes. The ecosystem includes a desktop app, a mobile‑first coding agent, and tools for syncing external knowledge bases.

  • Project
    modstart-lib/aigcpanel

    AIGCPanel is a cross‑platform desktop app (Electron + Vue 3) that bundles open‑source AI models for digital‑human video, multi‑model TTS/voice cloning, speech‑to‑text, and 25+ audio‑video utilities. It offers a visual drag‑and‑drop workflow editor and live‑stream comment automation (VIP tier), plus a CLI for scripting. Users install models via a built‑in market and can run everything locally or connect to remote/cloud services.

  • Project
    AGenUI/AGenUI

    AGenUI is an open‑source SDK that lets large language models stream UI descriptions (A2UI JSON) to native iOS, Android, and HarmonyOS apps. A shared C++ core parses the data, diffs a virtual component tree, and updates native views in real time, delivering smooth (≈120 fps) interactive experiences. It ships 22 built‑in components, a custom‑component API, function‑call integration, and a ready‑to‑use skill/studio for turning natural‑language prompts into valid UI JSON.

  • Project
    itwanger/PaiAgent

    PaiAgent is an open‑source, enterprise‑grade platform that lets users visually compose AI workflows with drag‑and‑drop nodes. It supports multiple large‑model providers via Spring AI, offers two execution engines (a classic DAG engine and a LangGraph4j state‑graph engine), includes a declarative “Skills” system for LLM‑driven function calls, and provides real‑time SSE debugging. The stack is React + TypeScript on the front‑end and Spring Boot 3 + Java 21 on the back‑end, with MySQL (and optional MinIO) for persistence.

  • Project
    zhayujie/CowAgent

    CowAgent is an open‑source, self‑hosted AI assistant that plans tasks, runs tools, keeps a personal knowledge base, and can operate as a team of cooperating agents. It supports many LLM providers, multimodal input, dozens of chat channels (Telegram, Slack, WeChat, etc.), a plug‑in skill system, and a three‑tier memory with nightly “Deep Dream” distillation. Install via a one‑line script or Docker, manage everything through a web console, and extend the system through the public Skill Hub or custom tool integrations.