Stars
Cross-Platform Production-ready C++ inference engine for YOLO models (v5-v12, YOLO26). Unified API for detection, segmentation, pose estimation, OBB, and classification. Built on ONNX Runtime and O…
完全基于本地rk3588（外设：摄像头和小喇叭），基于Qwen3-2B（rknn+rkllm）的语音聊天助手（其中rknn将摄像头实时拍到的画面分析得到图片特征，然后传给rkllm进行推理）（整个流程还用到了kws语音唤醒模型以及asr语音转文本模型和tts文本转语音模型），qwen3实际测试：非常聪明并且通晓世界上所有的事情，完全可以作为日常聊天助手，详见视频。readme.md以流程图和…
岩石薄片图像管理与智能分析系统，基于 React、FastAPI、PyTorch 与 SAM，支持用户管理、图片上传、矿物分类、鲕粒分割和 Agent 辅助分析。Rock Thin Section Image Management & Intelligent Analysis System based on React, FastAPI, PyTorch and SAM, supportin…
企业级 AI 开发平台，内置了开发环境管理、AI 模型管理、AI 任务管理、项目需求管理等能力，是真正面向专业开发团队的 AI 助手
Malware Classification is a deep learning project that detects malware families from malware image representations. It covers dataset exploration, preprocessing, ResNet50-based training, model expo…
RAGFlow: leading open-source RAG engine with Agent capabilities. MinerU: high-precision parser converting PDF/images/DOCX to Markdown/JSON. MinerU-Bridge: lightweight microservice integrating Miner…
aGeNtIc 🚀 time series anomaly detection on your df with AnomalyAgent().detect_anomalies(df)
使用HF-PEFT微调Qwen2.5-VL，学习仓库，包括但不限于Qwen2.5框架、HF微调框架、衍生模型(如monkeyOCR)微调
1773899415 / Flash-MinerU
Forked from OpenDCAI/Flash-MinerURay-based accelerator for MinerU VLM inference pipeline. Lightweight, multi-GPU friendly PDF → Markdown processing. 基于 Ray 的 MinerU VLM 推理加速器，轻量、低侵入，面向多 GPU / 国产算力环境的 PDF → Markdown 处理方案。
MinerU OCR application connects to SharePoint and calls LLM.
Turn paper/text/topic into editable research figures, technical route diagrams, and presentation slides.
Slimmed, cleaned and fine-tuned oh-my-opencode fork, consumes much less tokens
🚀 2026 最系统的 AI Agent 速成指南｜智能体实战教程 · 完整学习路径 + 实战项目 + 面试题库 · 对标大模型应用开发工程师岗位 · 覆盖LangChain / LangGraph / Coze / Dify / MCP / skills / LLM / RAG / 提示词 · 企业级部署与微调 · 从0到企业级落地 + 从学习到上线项目 + 面试准备一体化
把知名中文AI公众号蒸馏成 AI Skill，无痛阅读论文！Inspired by colleague-skill（同事skill）
The best-benchmarked open-source AI memory system. And it's free.
OpenChamber is a live Claude Code control panel with sessions, diffs, workspaces, notifications, mobile UX, PWA support, and real local provider integration.
Multi-user OpenChamber system based on Ubuntu 24.04 LTS with Docker containerization.
Desktop and web interface for OpenCode AI agent
💻 Build and manage projects efficiently with the OpenCode Web UI CLI, featuring a chat interface, file previews, and model selection.
A self-hosted web management panel for nanobot-ai
OfficeCLI is the first and best Office suite purpose-built for AI agents to read, edit, and automate Word, Excel, and PowerPoint files. Free, open-source, single binary, no Office installation requ…
Codebot 是类似 openclaw 的产品，对opencode cli进行接入，可视化和可沙箱运行等进行封装成应用程序，开箱即用，不需复杂部署
🎯 Nanobot WebUI — A Smarter, More Efficient Claude AI Assistant ✅ Coding & Bug Fixes ✅ Excel / PDF / PPT Processing ✅ Git Automation ✅ Visual Configuration Panel ✅ Q&A & Knowledge Management 24/7 r…
基于 Tauri + React 的 Nanobot 桌面端，提供本地可视化入口来启动/监控代理进程、对话并管理工作区文件。