A two-stage AI dialogue service that combines DeepSeek inference and Claude generation

The Allora MCP Server is an implementation based on the Model Context Protocol (MCP) that provides the function of obtaining machine learning inference data from the Allora network, enabling AI systems to seamlessly access Allora prediction market data.

Omni-NLI is a self-hosted multi-interface (REST and MCP) server that focuses on natural language inference tasks, used to verify the support, contradiction, or neutral relationship between texts, and can help reduce AI hallucination and improve application reliability.

The Deepseek Thinker MCP Server is an MCP service that provides Deepseek inference content, supporting both the OpenAI API and the local Ollama mode, and can be integrated into AI clients.

The Subconscious AI MCP Server is a tool based on the Model Context Protocol that allows users to run AI - driven conjoint experiments through AI assistants such as Claude and Cursor. It uses causal inference and synthetic population data for decision - making analysis and provides REST API and real - time update functions.

A FastMCP server implementation based on the Replicate API, focusing on providing resource-based access to AI model inference, especially good at image generation functions.

Forge MCP Server is a tool that automatically optimizes PyTorch models into high-performance CUDA/Triton kernels through 32 parallel AI agents, increasing inference speed by up to 14x and supporting multiple MCP-compatible AI programming assistants.

SHARP is an AI model developed by Apple Research, capable of quickly converting a single 2D photo into a 3D Gaussian Splat representation, achieving real-time conversion from photos to interactive 3D scenes, with an inference time of less than one second.

AI00 RWKV Server is an efficient inference API server based on the RWKV language model, supporting Vulkan acceleration and OpenAI-compatible interfaces.

Fluent MCP is a modern framework for building Model Context Protocol (MCP) servers with intelligent inference capabilities. It supports AI integration, tool separation, and offloading of complex inferences, and uses a dual - layer LLM architecture for efficient inference.

x402engine - mcp is an MCP server that provides HTTP 402 micropayment access to 38 pay - per - use APIs for AI agents, supporting payments in USDC and USDm, covering various services such as LLM inference, image generation, code execution, audio processing, and blockchain data.

MiniRAG-MCP is an MCP server wrapper built around the MiniRAG project, aiming to provide efficient and reliable Retrieval Augmented Generation (RAG) services for intelligent agent processes on local devices through client-managed LLM inference sampling.

IntelliGlow is a smart lighting system based on the MCP protocol that controls real smart bulbs through an AI assistant, supports voice commands, AI inference, and direct hardware control, and enables natural language interaction and intelligent lighting management.

Sensei MCP is a multi-role engineering tutor system that integrates 64 professional AI roles and provides engineering standards and suggestions through collaborative guidance. It can inject relevant engineering specifications before Claude's inference, supports multiple file types and context awareness, and has session memory and team collaboration functions.