Havuz

Typed structured extraction from PDFs, photos & text via any LLM — Instructor for Swift, document-first

Turn slide screenshots and generated images into editable PowerPoint decks with visual-layer splitting, OCR evidence, and QA.

Local-first desktop AI assistant built with Electron, FastAPI, and Ollama.

Reading companion for totally blind learners: the screen or a PDF read aloud in Arabic and English, offline first (NVDA add-on and a natural

Recordings in. Agent-ready evidence out. Local-first MCP for transcripts, keyframes, OCR, speakers, and wall-clock evidence.

Rust 反检测浏览器自动化 + 内置验证码 OCR 与图片滑块缺口距离识别 · 高并发爬虫 · 由极数本源(apizero.cn)出品 | Browser automation in Rust: anti-detect, built-in captcha OCR & slide

Local-first manga translator with AI-powered bubble detection, OCR, automatic translation, an editable web reader, browser extension, and lo

Smart launcher for you, and your AI agent.

🚀 让不支持视觉的大模型获得真·图片理解能力: 零安装、不破解PoW、OpenCV自动过登录验证码、用后即删的 DeepSeek C端识图模式 CLI

Local OCR, metadata automation and RAG document chat for Paperless-ngx using PaddleOCR and Ollama, designed for CPU-only self-hosted servers

Privacy-first document intelligence engine — parse PDFs, DOCX, PPTX, XLSX & CSV into AI-ready chunks for RAG pipelines. Includes HITL review

CPU-friendly sidecar that OCRs paperless-ngx documents with PaddleOCR PP-OCRv6 and writes text back via the API.

Autopilot for your Clash of Clans base on Google Play Games on PC — farming, wall upgrades, and auto base progression. PySide6 UI, OpenCV te

A Python library for automating and controlling macOS.

Private, searchable screen history for macOS.

Semark converts PDFs, Office files, HTML, and images into RAG-ready semantic Markdown using MinerU and VLM/LLM review, with chunks, source m

Interactive demo of a SOTA agentic OCR document approval flow

本地优先的全平台 Markdown 阅读器与编辑器：长文档语义分页、显示层非破坏纠错、Office/PDF/网页转 MD、离线 OCR、LaTeX 学术增强与 MCP 接入。官网地址：https://readmd.asia ； 爱发电：https://ifdian.n

Local and cloud GPU interference model orchestrator exposing OpenAI-compatible API from different engines

实时屏幕翻译覆盖层 | Real-time screen translation overlay with offline Bergamot engine, PaddleOCR + Tesseract

Self-hosted, privacy-first health records. Bring labs, visits, medications, and wearable data into one place you control — with biomarker tr

Async Docling sidecar that turns PDFs and office documents into Markdown, text, structured blocks, chunks, and extracted images for RAG. Pyt

Local-first handwriting studio for study-ready notebook pages, stylus annotations, and replay exports.

A vision backend for AI Agents — self-healing Claude Code Agent Skill. Routes images to Mimo/OpenAI/Ollama vision API.

Provider-independent DSH PDF reading tool powered by MinerU.

Yes Your Zen Tools

Ironclad-OCR is an asynchronous invoice ingestion and extraction service built for vendor PDFs that do not share a single stable layout.

Translate academic papers & monographs (PDF) into a single self-contained bilingual HTML — Chinese/original/side-by-side. Vendor-neutral, wo

企业微信智能客服 — 截图RPA + PaddleOCR + RAG，不依赖API，开箱即用

Cross-platform Rust computer-use MCP server for macOS and Windows: AX/UIA, screenshots, OCR, pointer and keyboard input, clipboard, stdio, a

AI-powered local-first renewal and app-wallet radar PWA

Your whole desktop context — everything you've seen, read, typed, and heard — as a single MCP your agent can use to understand you and how y

Free screenshot tool and screen recorder for Windows: floating thumbnails, quick editor, scrolling capture, text search with OCR, MP4 and GI

A 100% local, privacy-first alternative to Windows Recall — captures your screen, OCRs it, and lets you semantically search and chat with yo

Open-source control layer over PDF parsing that picks the right method, verifies output quality, and falls back automatically when results f

Kreuzberg v4 LTS — long-term support for the v4 line (legacy; superseded by xberg for v5+). MIT-licensed.

Clipboard-first macOS screenshot utility: select, release, paste — with app-agnostic scrolling capture

Visual bridge for text-only models and visual enhancement toolkit for multimodal AI agents — OCR, zoom, PDF/Office rendering, web vision and

即時辨識畫面中的文字並透過 AI 翻譯，然後以 Overlay 的形式顯示在原文上。 Recognizes on-screen text in real time, translates it with AI, and displays the translation as an

Turn a phone flip-through video, photos, or a PDF of a book into a clean, proofread EPUB/PDF/Markdown — local vision-LLM digitization with a

🌍 Real-time, offline screen translator for games & videos — OCR + NLLB-200 + subtitle overlay + neural voice dubbing that matches the speake

l3a0's Claude Code plugin marketplace — kindle-highlights: verbatim Kindle highlight extraction with truncation recovery

Permission-aware Agentic RAG for enterprise knowledge bases — folder ACLs, hybrid retrieval, OCR, grounded citations, and secure LLM evidenc

Your AI coding assistant can finally see what you're doing. Local-first screen context for Claude Code, Codex, Gemini CLI and Muse Code.

Every file tool in one open-source app. PDF, image, video, audio, OCR and ID photos, on your device, offline, with nothing uploaded.

基于 Shizuku + OCR 的淘金币自动任务助手，支持新旧版界面、跨应用任务与自定义任务规则。

Skim a video

保留排版的文档翻译工具：PDF / Word / PPT / Markdown / 字幕，图片、公式、表格与版式原样保留，译文落在原文位置。支持多语言方向、扫描件 OCR 与本地离线翻译（Ollama）。Windows / macOS 免安装，双击即用。

EasyOCR's accuracy in a single Rust binary: CRAFT text detection and gen2 CRNN recognition over ONNX, with no Python runtime.

MarkItDown GUI 是一款 Typora 风格的桌面文件转 Markdown 工具，支持 PDF、Word、PPT、Excel、图片、音频等 30+ 格式。集成 LLM 实现图片描述、全文分析、表单清洗。基于 Electron + React + Python Fast