pdf_to_md

Smart PDF to Markdown converter with intelligent heading detection, automatic header/footer removal, orphan fragment merging, and image export. Features a user-friendly GUI with preview mode, persistent settings, and per-page error recovery. Optimized for Obsidian and other Markdown-based note-taking workflows.

V-Thinker

V-Thinker is a general-purpose multimodal reasoning assistant that enables Interactive Thinking with Images through end-to-end reinforcement learning. Unlike traditional vision-language models, V-Thinker actively interacts with visual content—editing, annotating, and transforming images to simplify complex problems.

Netlib-Keep-Alive

Netlib.re 单/多账号登录保活脚本

Schema-Action-Querying

Schema‑Action‑Querying: An open‑source multi‑table Text‑to‑Action system for Excel/CSV files. Use small local 3B‑parameter language models to automatically identify tables, columns and joins — no database setup, no cloud service required.

MCP-oura

Oura MCP Server A Model Context Protocolhttps://modelcontextprotocol.io/introduction MCP server that provides access to the Oura API. It allows language models to query sleep, readiness, and resilience data from Oura API. All Documents > Call for translators! We're looking for translato

FaithC

Official Torch/CUDA Implementation of Faithful Contouring

SmartResume

SmartResume 是一个面向版面结构的智能简历解析系统，系统支持 PDF、图片及常见 Office 文档格式，融合 OCR 与 PDF 元数据完成文本提取，结合版面检测重建阅读顺序，并通过 LLM 将内容转换为结构化字段（如：基本信息、教育经历、工作经历等）。系统同时支持远程 API 和本地模型部署，提供灵活的使用方式。

MadAssistantDuet

二重螺旋小助手/MadAssistantDuet is an assistant for Duet Night Abyss.

DeepOCR

A reproduction of the Deepseek-OCR model based on the VILA codebase. DeepOCR explores context optical compression through vision-text token compression, achieving competitive OCR performance with minimal vision tokens.

linux-desktop-gremlin

KurtVelasco's Desktop Gremlin, now on Linux!

GPT-OSS

From-scratch implementation of OpenAI's GPT-OSS model in Python. No Torch, No GPUs.

ComfyUI_SuperScaler

暂无简介