Havuz

Myna Recorder — a Windows macro recorder you can read and edit. Image anchors, an auto clicker, an AI assistant that writes macros, Agent mo

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

Turn your own PDF textbooks into an AI-searchable knowledge base and structured, fully-cited notes — figures included. Local-first, token-fr

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

74 free tools that run 100% in your browser: photo editor, AI background remover (photo, GIF, video), collage maker, speech to text, PDF edi

Private, native macOS app to capture pages, text, notes, links, and images—and find them instantly with full-text search and OCR. Open sourc

EchoTest — Windows 桌面与安卓自动化测试工作台：操作录制与重放、原生 UI / 图像 / OCR 定位、低代码与 Python 用例、执行报告和 MCP 接入。

The vision plugin for OpenCode that truly understands images. Inspect, read, and reason about any screenshot or picture with deeper understa

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

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

Smart launcher for you, and your AI agent.

BetterAIChat2 (BAIC2) — 本地优先的 Android AI 智能体：57 个真实设备工具（无 GMS：截屏 OCR / UI 自动化 / 离线定位 / 文件 / 网页 / 提醒 / 通知触发自动化 / 技能与子代理）、仿生记忆（别名、时间线、自省巩固、出处、

情圣 · Claude Code 中文恋爱教练技能 · 微信/探探/Soul/Bumble/青藤之恋聊天截图分析 · 高情商回复生成 · 7阶段关系推进

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

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.

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

给 DeepSeek 补上「眼睛和耳朵」的多模态视觉插件：看图 / OCR / 物体检测 / 视频理解 / 语音转写 / 截图直读，一键安装（DSH 插件）。

A Python library for automating and controlling macOS.

Open-source video processing core and CLI. Search and annotate local videos with your own model endpoints.

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

专治收藏夹吃灰 —— 让存过的小红书笔记这次真的找得回来。不是爬虫，不用你的账号登录态发请求，封控风险低。拖拽导入 + 图片 OCR + 自动分类，全程本地，不需要 AI API key。macOS 桌面 App。

Pay-per-call APIs and MCP services for AI agents: document OCR, document analysis, media transcription, browser sessions, and agent inboxes.

The free, open-source desktop alternative to Adobe Acrobat for Windows and macOS. Built on BentoPDF.

Self-hosted AI workbench for a company LAN. One command on a Windows server sets up login, roster, model gateway, company disk and knowledge

Free, Privacy first open-source manga translator. Run everything locally on your GPU, use Gemini, or connect your own LLM. Bubble detection

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

Free, open-source screenshot tool, screen recorder, and video editor for Mac. Auto-zoom, smooth cursor, captions, OCR, scrolling capture, an

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

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

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

A consistent, fair, benchmark for structured extraction.

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

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

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

Skim a video

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

MCP server that turns any video — YouTube, Instagram, TikTok, Loom, X, Vimeo, direct URLs, local files — into transcripts, key frames, OCR t

ADB 滑动截图 + 视觉大模型识别题目，按章节导出 JSONL / Markdown / index.json。GUI（新拟物界面）+ CLI（Agent 友好）+ 自然语言三种用法。

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

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

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

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

Lightweight text and scans processing: embedding, document processing, OCR, OMR, etc, with inference via ggml in pure C++

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

🚀 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

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

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

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

🪁 Read any manga in your language directly in-browser. 100% local-first AI translation with WebGPU OCR, clean background inpainting, and stu