Stars
Local-first, open-source AI assistant for your data. Unify tasks, notes, docs, photos, and bookmarks. Private, self-hosted, and extensible via APIs.
Qwen-TTS offers a robust voice synthesis service using FastAPI, supporting bilingual and dialect options. Explore seamless audio generation on GitHub! 🚀🌟
Like Claude Code, but Koding with DeepSeek V3.1, Kimi2, GLM4.5, Qwen Coder etc.（welcome to use Kode to summit PR)
Lightweight coding agent that runs in your terminal
[ICCV2025] Official Pytorch Implementation of TinyViM
A user-friendly PDF-to-Markdown conversion tool based on Mineru.
智慧安防平台，基于asmoboot项目：https://github.com/RotaNova/asmoboot 具备高效、稳定的流媒体，支持主流摄像头接入。定制AI识别，跨境追踪。边缘计算，AI使能指挥大厅。
数据分析智能体 (Data Analysis Agent)：基于LLM的智能数据分析智能体
MiniCPM-V 4.5: A GPT-4o Level MLLM for Single Image, Multi Image and High-FPS Video Understanding on Your Phone
VideoChat 是一款智能音视频内容解读助手，支持批量上传音视频文件并自动转录为文字。通过 AI 技术，它能快速生成内容总结、详细解读和思维导图，并提供智能对话功能，帮助用户更高效地理解和分析音视频内容。支持多种格式导出字幕文件。
Finetuning MiniCPM-V-2_6 for Object Detection Task
Youtu-GraphRAG boosts cost efficiency, inference accuracy, and cross-domain adaptability, pushing the boundaries of performance in complex QA.
SciAgent is a reasoning agent system for scientific task reasoning.
DataFlex is a data-centric training framework that enhances model performance by either selecting the most influential samples, optimizing their weights, or adjusting their mixing ratios.
Sample Excel add-in and Python script code to run an agent using LLM from an Excel function
A framework for building, orchestrating and deploying AI agents and multi-agent workflows with support for Python and .NET.
A simple yet powerful agent framework that delivers with open-source models
Easy Data Preparation with latest LLMs-based Operators and Pipelines.
A modern web UI for the Qwen ASR model, featuring audio recording, PWA support, Picture-in-Picture mode, and local caching for fast, accurate transcriptions.
A free and open source, self hosted Ai based live meeting note taker and minutes summary generator that can completely run in your Local device (Mac OS and windows OS Support added. Working on addi…
💫 Toolkit to help you get started with Spec-Driven Development
Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything
[ECCV 2024] Official implementation of the paper "Semantic-SAM: Segment and Recognize Anything at Any Granularity"