deepseek mcp with MoE

Feature-rich dev environment combining UV package management, Open Interpreter integration, containerized Python workflows, and robust tooling for rapid development.

Claude-enabled workflow that automatically transfers extracted invoice data into Google Sheets.

Interactive Kubernetes command runner with kubeconfig support, robust output piping, automatic kubectl setup, and clear, actionable error messages.

A versatile Next.js client enabling multi-LLM chats with real-time streaming and local history.

Primitive modular gateway coordinating three back-box agents to progressively enrich content via a shared, cross-team workflow.

Secure terminal with controlled command execution and built-in npm operations, featuring timeouts, environment variables, and directory controls for streamlined workflows.

A lightweight note manager enabling storage, summaries, and organization for calendar workflows.

Local note storage with note:// access, summarize-notes prompt, and add-note tool for seamless comfy UI integration.

A Memory Graph focused on real-time type inference and pattern-based categorization across Claude Desktop via cross-language MCP tooling.

LET AI PLAY GLOBAL THERMONUCLEAR WAR. This is an MCP Server for Introversion Software's 2007 game DEFCON.

Example code for Anthropic MCP client.

macOS compatible version of mcp-pdf-tools

LangChain4j + Quarkus playground (RAG, MCP, A2A, ...)

modelcontextprotocol java sdk

🤖 Build personalized intelligent agents easily with AgentX, a platform that simplifies creation using natural language and integrated tools.

[DOC] Some experimentations with ChatGPT and IGNF APIs (french)

LLM engine with MCP capabilities and Discord interface

My MCP servers

A TypeScript-driven backend project designed to power a rich, customizable portfolio experience, and show-case of others Projects

All-in-one web analysis toolkit with JS-rendered HTML, content extraction, visuals, and audits tailored for developer workstreams.

A TypeScript MCP playground showcasing host and server interactions, tool calls, and function calling patterns for rapid experimentation and learning.

Modern, full-stack Kanban with FastAPI/Next.js, real-time updates, clean architecture, and MCP-powered AI tool calls.

TypeScript toolkit for building and monitoring context-driven clients and services with strong typing, observability, and streamlined integration.