Havuz

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

claude-real-video, video dosyası veya URL’den sahne değişimlerine göre seçilmiş kareler ve transcript çıkarıp bunları LLM’lerin inceleyebileceği yerel çıktılara dönüştürür.

Neden yükseliyor · Video analizini mevcut LLM/agent iş akışlarına ekleyen kurulumu kolay bir araç sunuyor; README’de Hacker News ön sayfa rozeti var. 89 günde 2.185 yıldız ve son 28 günde 16 commit ile 4 farklı yazar, ilginin yanında yakın dönem katkı etkinliğine de işaret ediyor; yıldızlar tek başına kullanım veya kalite kanıtı değil.

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

With DocSlight, precisely parse and extract data from any document, including PDFs, scans, images, and Office files. It is an open-source AI

Screen Translator, Android ekranındaki yazıları OCR ile tanıyıp çeviren ve sonucu ekranın üzerine yerleştiren bir uygulamadır.

Neden yükseliyor · 97 günde 906 yıldız alması, özellikle oyun ve manga çevirisi gibi belirgin bir kullanım alanına hitap ettiğine işaret ediyor. Ancak son 28 günde 2 commit ve 1 farklı yazar bilgisi, ilginin sürdürülebilir geliştirme faaliyetiyle desteklendiğine dair sınırlı kanıt sunuyor.

Private, self-hosted document chat for attorneys: parse legal PDFs and query them with local open-source LLMs (Ollama) + verifiable page cit

Turn any document into clean, AI-ready Markdown. Local-first desktop app: reads scanned PDFs, batches folders, runs offline, and uses far fe

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

Zero-token, on-device vision for AI agents — OCR, pixel-exact UI targeting, and face grouping on Apple Vision. Pure Swift, single binary, no

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

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

Context-aware technical term explanations for Chrome and Edge, powered by Rust/WASM and optional LLMs.

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

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

📋 Clipboard manager for vibe coders — native macOS menu-bar app. Text & image history, screen capture + annotation, scrolling capture, scree

Lemmary turns scans, PDFs, and office files into an organized library you can search, review, and research in plain language.

macOS CLI for OCR and searchable PDFs using Apple's Vision framework

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

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

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

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

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

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

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

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

Interactive demo of a SOTA agentic OCR document approval flow

Sleek, mobile-friendly web UI for NVIDIA LocateAnything-3B — open-vocabulary object detection & grounding on your own GPU, via one docker co

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

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

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

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

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

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

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

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

ParseCrate: self-hosted document processing API powered by Docling and docling-serve. Converts PDF, DOCX, PPTX, HTML, and more to Markdown/J

PureDocBench: source-traceable benchmark for document parsing across clean, degraded, and real-world settings

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

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

Screenshots, beautifully simple. A fast, local-first screenshot tool for macOS and Windows: hover to capture windows, annotate, beautify and

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

Aetox harness: a local-first Windows AI environment - model, skills, team and memory as one system. Two doors - an Assistant that adapts to

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

A skill tool for Codex and Claude Code that converts images, PDFs, and image-based PPTX files into editable PowerPoint presentations.

Self-hosted URL- and file-to-Markdown service for humans and AI agents - web pages, documents, images, audio, YouTube. PWA + REST + MCP + Cl

An all-in-one PDF and Office document platform: self-hosted, open source, under your control. 整合式 PDF / Office 文件處理平台，自架、開源、可控。

A lightweight, system-wide AI text-selection assistant that supports custom LLM APIs and screenshot-based AI image recognition.轻量级系统全局ai划词助手

Open-source desktop OCR, AI translation, editing and inpainting tool for user-provided manga and comic images.

KillerPDF, Windows için yerel çalışan kapsamlı bir PDF düzenleyicisi ve yeniden kullanılabilir bir .NET PDF işleme engine'i sunuyor.

Neden yükseliyor · 4.001 yıldız ve son 28 günde 257 commit, projeye belirgin ilgi ve yüksek geliştirme temposu gösteriyor. Geniş özellik kapsamı, açık kaynak olması ve ayrı bir .NET engine sunması dikkat çekiyor; ancak bu veriler büyümenin özel nedenini tek başına açıklamıyor. Son 28 günde 3 farklı yazar olması, hareketliliğin az sayıda katkıcıda yoğunlaştığını düşündürüyor.

An AI companion that lives on your desktop - OpenGuider watches your screen, listens to your voice, and guides every step with clear actions