Text Tools

Text Tools DeepSeek-OCR WebUI: Batch OCR with Markdown Tables and Visual Bounding Boxes

Upload multiple images and run OCR with DeepSeek-OCR. Outputs clean Markdown tables, HTML, or annotated images. Runs locally or via Docker.

Text Tools Paperless GPT: Smarter OCR and Auto-Tagging for Paperless-NGX

Enhance Paperless-NGX with AI-driven OCR and automated tagging. Fix illegible scans using GPT-4o or Ollama and eliminate the need for manual filing.

Automation Tools Skill Seeker: Convert Any Documentation Site Into Claude AI Skills

Skill Seeker scrapes documentation, organizes content, and packages production-ready Claude skills. Features include zero API costs, local AI enhancement, and support for 40,000+ pages.

Voice & Speech Tools Index-TTS-LoRA: Fine-Tuning Voice Models for Natural Speech Synthesis

Learn how to extract audio tokens, fine-tune with LoRA, and generate natural speech. Includes training commands, inference steps, and WER benchmarks compared to the base model.

AI Face Tools BananaFace: Open Source AI Stylist for Consistent Character Design

BananaFace is an open source AI styling tool that generates high-fidelity character portraits with 44 adjustable parameters. Supports text-to-image and image-to-image modes.

MCP Services Google Analytics MCP Server: Query GA4 Data With Gemini CLI

Connect Google Analytics to Gemini CLI with the GA MCP server. Run reports, list accounts, and get real-time data using natural language prompts.

AI Agent Frameworks Cogency: Build AI Agents in Python with Transparent ReAct Loops

Cogency is a Python library for building production-ready conversational AI agents. Write three lines of code, integrate tools, and monitor every reasoning step via live streaming.