Havuz

모두 파싱해버리겠다 — HWP·HWPX·PDF·Office 문서를 Markdown으로. 양식 자동 채우기와 신구대조를 갖춘 CLI·MCP 서버 | Convert Korean documents (HWP, HWPX, PDF, Office) to Markd

Self-hosted web scraper, crawler and document parser for AI agents: URLs, PDFs with OCR and Office files to clean Markdown/JSON. Firecrawl-

Turn your cameras into Home Assistant sensors with a local AI: garage door open/closed, people and cars, water, gas and power meters read by

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.

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

ParseBench - A Document Parsing Benchmark for AI Agents

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

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

A consistent, fair, benchmark for structured extraction.

lnwjud — local AI-agent runtime & MCP gateway

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

Local-first translation studio for manga, manhwa, and manhua.

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

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

Local-first AI workbench for OCR, transcription, translation, image generation, mind maps and composable workflows. Built for DGX Spark.

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

Yes Your Zen Tools

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

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。

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

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

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

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

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

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

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

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

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,

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

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

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.

🚀 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

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

Developed a Document Intelligence platform that automates document processing using OCR, NLP, and AI to extract, classify, and validate stru

Strip the personal data out of a document before you paste it into an AI. Converts PDF, Office, scans and email to Markdown and removes name

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

Local media studio for the Tiiny Pocket: desktop app (Windows, macOS, Linux) or Docker. Images, OCR & documents, chat with tools, voice, mus