Stars
This repository provides an implementation of "A Simple yet Effective Training-free Prompt-free Approach to Chinese Spelling Correction Based on Large Language Models" and "A Training-free LLM-base…
Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.
Turn any idea, plan, or codebase into a beautiful interactive diagram. An agent skill for Claude Code, Codex, and more.
Orca is the ADE for working with a fleet of parallel agents. Run any coding agent with your own subscription. Available on desktop, mobile and remote runtime.
本地优先的跨平台 Claude Code / AI Agent 桌面工作台：多 Agent 协作、Git Worktree、代码 Diff、技能市场、多模型、Computer Use、桌面宠物；支持微信、飞书、钉钉及 H5 等远程访问。 | Local-first Claude Code / AI Agent desktop workspace: multi-agent teams, Git…
Pure python3 implementation for working with iDevices (iPhone, etc...).
A free, open-source Windows desktop organizer with native-feeling WinUI 3 widgets.
DeepSeek Harness 零代码桌面端｜一键启动，支持 Windows 与 macOS；内置插件发现、热点插件推送、一键安装与管理、AI 智能推荐和视觉增强。
DeepSeek Harness: Everything is a Plugin.
A self-improving RLM agent for coding workflows and long-running autonomous tasks.
The official repo for “DocScanner: Robust Document Image Rectification with Progressive Learning”, IJCV, 2025.
3FUI 是 ffmpeg 在 Windows 上的轻度专业交互外壳，收录大量参数，界面美观，交互友好。此项目面向国内使用环境，让普通人也能够轻松压制视频和转换格式。
A modern desktop application for PDF & document manipulation — clean metadata, split chapters, merge Markdown, and convert between formats.
把书、长视频、播客等高价值内容蒸馏成可执行的 Agent Skills（Distill high-value content from books, long-form videos, podcasts, and more into executable Agent Skills）
A feature-rich command-line audio/video downloader
适用于问卷星、腾讯问卷、Credamo见数平台的纯HTTP高并发提交程序
一个基于大语言模型和LangChain开发的中文文本处理系统，提供实体一致性检测和中文语法纠错功能。
Local File Converter: Supports PDF2Image, Image2PDF, Word2PDF, PDF2Word, PPT2PDF, Excel2PDF, CSV2Excel, Excel2CSV, CSV2PDF, Word2Text, Text2Word, Text2PDF, PDF2Text.
pdf文件处理工具, 包含: pdf剪切, pdf旋转, pdf合并, pdf拆分, pdf添加页码, pdf转图片, word转pdf等功能
SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer
fastllm是后端无依赖的高性能大模型推理库。同时支持张量并行推理稠密模型和混合模式推理MOE模型，任意10G以上显卡即可推理满血DeepSeek。双路9004/9005服务器+单显卡部署DeepSeek满血满精度原版模型，单并发20tps；INT4量化模型单并发30tps，多并发可达60+。
GPT-Image-2 API and Prompts
基于pycorrector以及chatglm3-6b的文本纠错