Image Tools

Image Tools GRAG: Continuous Image Editing Control for DiT Models

Group Relative Attention Guidance adds smooth, fine-grained control to DiT image editing. Adjust intensity with a single parameter and no training.

Voice & Speech Tools VibeVoice: Long-Form Multi-Speaker TTS for Natural Dialogue Generation

VibeVoice generates podcast-style dialogues featuring up to four speakers for durations of up to 90 minutes. It utilizes a specialized tokenizer and diffusion framework. Includes installation guides and demos.

LLM Tooling LLM Bridge: A Unified API Schema for OpenAI, Claude, and Gemini

LLM Bridge streamlines communication between OpenAI, Anthropic, and Google Gemini APIs with zero data loss. Utilize a single, type-safe universal format that fully supports tool calls and multimodal content.

AI Agent Tools MaskSearch: Training LLMs for Expert-Level Search Capabilities

MaskSearch utilizes retrieval augmented mask prediction to train LLM search agents that excel on HotpotQA, Musique, and FreshQA. Explore the framework and benchmark results.

System Utilities Ventoy USB Tool: Boot Multiple ISOs Without Reformatting

Ventoy allows you to copy ISO, WIM, IMG, and VHD(x) files directly to a USB drive for immediate booting. No reformatting required. Supports over 1,200 OS images, UEFI Secure Boot, and various partition styles.

Web Scraping Tools Crawl4AI RAG MCP Server: Web Crawling and Vector Search for AI Agents

The Crawl4AI RAG MCP Server enables AI agents to crawl websites, store content in Supabase, and perform semantic queries. It is compatible with Claude Desktop and other MCP-enabled clients.