High-performance PDF processing with multilingual text/table extraction, image optimization, deep learning classification, and cross-language similarity to deliver structured insights.

Unified OpenAI-compatible LLM API across 10+ providers with load balancing, fallbacks, retries, semantic caching, and observability.

On-device, privacy-first text generation via Apple Foundation Models, integrated as an MCP server.

Model Context Protocol (MCP) server implementation for semantic vector search and memory management using TxtAI. This server provides a robust API for storing, retrieving, and managing text-based memories with semantic vector database search capabilities. You can use Claude and Cline AI as well.

Python-based service for ML model provenance and lineage with RESTful API, dataset management, and Croissant metadata validation.

Production-ready Notion-integrated memory toolkit featuring automatic tool discovery and robust error handling.

Delivers Snowflake Cortex capabilities—Search, Analyst, and Agent—with a dynamic payload builder, exposing tools to clients via stdio/sockets and streaming responses.

Rust-based, high-performance framework enabling AI models to access external context via multi-transport, resources, and secure interfaces.

Interactive, semi-automated verified program synthesis for Dafny that blends LLMs with symbolic reasoning to accelerate proofs and skeletonize verification workflows.

Simple MCP Client CLI Implementation Using LangChain ReAct Agent / Python

Polymind Bot offers multi-model AI with Model Context Protocol integration, Mermaid diagrams, and group collaboration for advanced Telegram-based AI workflows.

Retrieval-Augmented Generation with a Qdrant-backed vector store, offering Ollama or OpenAI embeddings, multi-format document ingestion, and Claude Desktop integration.

Unifies embedding, vector storage, semantic search, and AI answer generation using Moorcheh's models for fast, contextual data insights.

An inherently interpretable classifier that learns multi-level concept prototypes using CKA and CCD losses, enabling faithful explanations and strong few-shot generalization.

A curated collection of reference designs showcasing modular tool integration, agents, and browser interactions for rapid prototyping.

A lightweight analysis proxy that records LLM call parameters and responses, supports multiple modes, and provides real-time logs and mocks.

moondream mcp

Private, local AI flow enabling WeChat interactions with ERP data through Ollama models and private knowledge bases.

RagDocs enables semantic search and document management using Qdrant vector storage with Ollama or OpenAI embeddings.

Modular image-generation server powered by Flux Schnell with configurable dimensions and MCP-friendly integration.

AI SDK for building AI-powered applications in Go

mcp chat analysis server

A Go implementation of an MCP (Model Context Protocol) server tools

Lightweight medical segmentation with prompts and tiny ViT backbone, trainable on a single GPU in one day.