Havuz

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Kreuzberg v4 LTS — long-term support for the v4 line (legacy; superseded by xberg for v5+).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

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

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.

Local-first semantic search engine for your files — hybrid BM25 + vector + HyDE search over docs, PDFs, images, audio and video. 100% offlin

TalkTact · 微信聊天助手（LSPosed 模块）：聊天页悬浮候选回复卡片（★最推荐+理由、单条改写），多套提示词 skill，角色关系档案；直通/模型分级双模式，本地代理让 API Key 不出 App 进程，会话白名单，以及本机离线的图片文字识别（OCR）。只填输入框

Slate — a fast, native, privacy-first PDF reader & editor. Free & open source (AGPL-3.0). Built with Rust + Tauri.

Fully local document intelligence for DeepSeek Harness. Parse PDF, Office files, images, and scanned documents with offline OCR. | DeepSeek

本地优先的视频字幕 OCR 工具：提取硬字幕/软字幕，自动定位字幕区域，导出 SRT/TXT，并可选用大模型修正文案。

Open MIT JSON Schema 2020-12 spec for SlimSnap captures. Bounding boxes, OCR text, extracted colors, annotations with intent and target_ref.

Offline AI search for photos, video & audio, powered by EmbeddingGemma 2 — jump to the exact second in a video. macOS · Windows · Docker/NAS

The marketplace for verifiable AI outcomes: state a task, get a fixed price upfront, and Primitive Bench routes across tools to complete it,

AI-Powered Financial Analysis Desktop App — 7 Engines, 17+ Ratios, Bankruptcy Prediction, TSETMC Live, 100% Offline

Lightweight Doc-to-agent-ready knowledge pipeline. Three-stage Bronze→Silver→Gold architecture extracts structured elements, page content, a

Open-source AI-assisted HR onboarding for Feishu/Lark: configurable workflows, document OCR and review, Bitable sync, reminders, and a zero-

Hugging Face recipes: run OCR, transcription, classification, embeddings and more over a Hub dataset in one command, locally or on HF Jobs.

Edit, convert, and transform documents across PDFs, Office formats, HTML, TXT, CSV, RTF, JSON, and images with ComPDF Self-hosted, an open-s

Agentic RAG Harness for long documents, Tree and Graph based reasoning. Cited answers down to the pixel

Best Real-Time Screen OCR Translator for Windows and Web API 2026

Best Roblox Tower Heroes Auto Farmer with OCR Macros 2026

Agent skills for LandingAI's Agentic Document Extraction (ADE) — production-ready document AI for agentic coding assistants

On-device subject cutouts, image labels, and OCR for React Native. Apple Vision (iOS) · Google ML Kit (Android). Built with Nitro Modules.

Faithful, 100% local OCR Chrome extension | code, prose, formulas (LaTeX) & tables. No server, nothing leaves your device, no hallucinated t

A unified intelligence workspace combining Canvas OCR, Sobel & Canny edge shaders, YouTube transcript analysis, and interactive Mermaid.js d

Part of the KDAN ecosystem, DocSlight offers document parsing, OCR, and data extraction that turn PDFs, scans, images, and Office files into

Can my GPU run this? Pick a GPU to get 3 fitting AI models, quantization, VRAM, speed ranges, and run commands. 한국어·English.

Translate books and documents with LLMs, featuring glossary extraction, review, and polishing pipelines.

oo is OOMOL's CLI toolkit. Everything can be done in the CLI.

Advanced Windows & Web Automation Tool. Features: Record Clicks/Scrolls, Anti-ban (Random Delay), Playwright integration, and OCR.

Local-first OCR-VLM multimodal document retrieval and independent evaluation prototype.

Production-ready Expo Module for on-device text recognition (OCR) using Google ML Kit Text Recognition v2 + OCRTextOverlay

macOS CLI and HTTP OCR tool for converting document images to Markdown.

Self-hosted document automation, automatic tagging and approval-gated companion for Paperless-ngx.

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

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

🚀 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

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

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

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

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

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