Comprehensive blockchain AI toolkit enabling on-chain data analytics, wallet interactions, and NLP-driven agent tasks across multiple chains.

Transforms prompts into high-quality raster and vector graphics using Flux Schnell and Recraft SVG, with local processing and MCP-wide compatibility.

A self-hosted web UI that simplifies AI experimentation and testing for Java developers. It provides playgrounds for all major vector databases and MCP tools, supports intuitive interaction with LLMs, and enables rapid development and testing of RAG workflows, MCP integrations, and unified chat experiences.

Unified interface for MariaDB data access with SQL and embedding-powered retrieval, enabling AI-driven insights across relational and vector stores.

Open-source desktop AI with local-first memory and voice UI, offering private, extensible MCP integrations.

Zero-install AI-powered web search using Perplexity Sonar models with citations, featuring robust caching, deduplication, and strict TypeScript.

Connects AI assistants to PapersWithCode for searching, retrieving, and parsing papers, authors, datasets, and code repositories.

Generates photorealistic images using Google Imagen 3.0 via Gemini API with flexible local deployment and proxy support for seamless workflows.

GPU-accelerated vision toolset enabling zero-shot object detection and precise object zoom for LLM-enabled analysis

Fetches recent positive articles via NewsAPI and ranks them using Cohere-based sentiment scoring for quick uplifting content.

The complete, 100% native AI framework for Delphi. Build powerful applications with RAG, Agents, workflow orchestration, and a universal LLM connector.

A WhatsApp bot that can participate in group conversations, powered by AI. The bot monitors group messages and responds when mentioned.

Dual-mode MCP server delivering Deepseek's reasoning outputs via OpenAI API or Ollama, with Claude Desktop integration and flexible deployment options.

Hands-on Quarkus LangChain4j workshop guiding stepwise AI-powered app development with runnable local demo.

MCP Web UI is a web-based user interface that serves as a Host within the Model Context Protocol (MCP) architecture. It provides a powerful and user-friendly interface for interacting with Large Language Models (LLMs) while managing context aggregation and coordination between clients and servers.

Unified TiDB AI SDK enabling automatic embeddings, multi-modal storage, and vector/full-text/hybrid search with transaction safety.

Unified model integration layer enabling seamless provider switching, standard protocol compatibility, and programmable AI flows for scalable agents.

Configurable image generation tool via Replicate Flux with Claude Desktop integration and model selection.

Lightweight single-file HTML frontend for chatbots with OpenAI-format support, multiple backends, and MCP IPC integration.

Browser-first platform enabling visual AI workflows with local LLM inference, node-based orchestration, and integrated vector search for rich experimentation.

DLP-based audio extraction paired with Whisper-1 for precise, long-form YouTube transcripts delivered in chunks.

Semantic documentation search powered by Qdrant with flexible embedding backends for fast, contextual retrieval across docs.

A SPARQL query generation toolkit powered by LLMs with metadata-aware validation and retrieval-augmented generation for federated endpoints.

Text-to-image generation powered by Amazon Bedrock Nova Canvas with deterministic seeds, negative prompts, and flexible sizing.