bytefer / macos-vision-ocr
A powerful command-line OCR tool built with Apple's Vision framework, supporting single image and batch processing with detailed positional information output.
☆40Updated last month
Alternatives and similar repositories for macos-vision-ocr:
Users that are interested in macos-vision-ocr are comparing it to the libraries listed below
- Implementing OCR with a local visual model run by ollama.☆188Updated last month
- An JS web client for connecting to Pipecat bots with voice and vision☆42Updated last month
- Use cloudflare worker and rust wasm to build an image processing service. 使用 Cloudflare Worker 和 Rust WASM 构建图像处理服务☆28Updated 3 months ago
- A Chrome extension built with WXT and shadcn/ui that helps you polish text with AI capabilities. Simply select any text on a webpage to t…☆56Updated last week
- 轻松理解和使用 Midjourney 提示词☆16Updated 3 months ago
- Try out our Live version here, no need to add API keys, just select model and try it out☆98Updated 2 weeks ago
- Free and open-source editor for dbml online.☆31Updated 8 months ago
- 🧩 / 🚀 PluginTemplate - This is the plugin template for LobeChat plugin development.☆50Updated 6 months ago
- Maybe the best template based on wxt.☆74Updated 3 weeks ago
- Open-source observability for your LLM application.☆47Updated 2 weeks ago
- YC companies example built on Trieve☆14Updated 5 months ago
- Easy to deploy.A cloud service for python code interpreter sandbox for Code-Interpreter.☆48Updated 10 months ago
- 🔥🔥 Kokoro in Rust. https://huggingface.co/hexgrad/Kokoro-82M Insanely fast, realtime TTS with high quality you ever have.☆169Updated this week
- ☆14Updated 5 months ago
- Edgeone pages templates☆43Updated last week
- You need a few lines of JS, not a vector database.☆17Updated 3 months ago
- 基于 OpenAI Realtime Console 修改的语音聊天应用。支持定义 api base url。☆30Updated 3 months ago
- Chat with any website on your local machine☆72Updated 6 months ago
- A user-friendly DeepSeek AI node, similar to OpenAI, designed to enhance your workflow.☆83Updated 2 months ago
- Parse PDFs into markdown using Vision LLMs☆194Updated 2 weeks ago
- Opensource AI editor, All you need is editor! Studio B3 is a sophisticated editor designed for content creation, catering to various form…☆57Updated 2 months ago
- ZByAI - AI-Enhanced Search☆49Updated 5 months ago
- The web API server that runs program codes in an isolated environment using Docker.☆16Updated last year
- A plug-and-play, highly customizable block-based rich text editor. Supports block/inlineBlock development with any framework, including …☆140Updated 9 months ago
- 📊 Lobe Charts - React modern charts components built on recharts☆32Updated last week
- 🔥 LitLytics - an affordable, simple analytics platform that leverages LLMs to automate data analysis☆93Updated last month
- Gemini Multimodal Live + WebRTC in a single `app.ts`☆171Updated 3 weeks ago
- One-click Docker APPs of Open-source Code Interpreter Projects.☆60Updated last year
- ☆36Updated this week
- Rust implementation of Surya☆56Updated 2 weeks ago