"Créer des systèmes de prompt pour les modèles de langage (LLM)" matching MCP servers:

Connects AI agents to a collective creativity platform where they can publish, read, and explore creative connections (bisociations) between concepts from different domains.

A Model Context Protocol server that saves prompts with timestamps and allows users to list previously saved prompts for Claude Desktop.

Provides personalized Data Engineering learning updates by fetching recent news about DE concepts, patterns, and technologies, while tracking user knowledge to present only new information relevant to their learning journey.

Converts meetings, chats, and notes into reusable knowledge for a venture capital firm, enabling knowledge capture and retrieval via Claude or Codex.

A local-first memory cartridge for MCP-compatible AI clients, providing durable, inspectable, and auditable memory storage with a read-only-by-default MCP server.

A local-only MCP server that uses SQLite to store, search, and manage a personal library of AI prompts. It enables developers to organize and reuse prompts across multiple AI clients like Claude and Cursor while keeping all data on their local machine.

Graph-level operations for Karpathy LLM Wiki knowledge bases, enabling LLM agents via MCP and humans via CLI to perform structured graph surgery including node/edge CRUD, wikilink management, index rebuilding, and graph metrics.

Enables semantic search and management of private, encrypted knowledge bases via MCP, supporting document upload, text and URL ingestion, document listing, and removal through natural language.

Git-driven MCP server that manages and provides prompt templates with Handlebars support, enabling teams to collaborate on and version-control reusable, dynamic prompts across AI editors like Cursor and Claude Desktop.

Persistent markdown wiki for your AI agent, built on Karpathy's LLM wiki gist.

Builds a local, citation-aware wiki from an approved project scope and exposes it as an MCP server with a single read-only tool for agents to explore the wiki.

Enables creation of persistent, compounding knowledge bases using Karpathy's LLM Wiki pattern with LLM-maintained markdown wikis. Supports automated ingestion, cross-referencing, synthesis, and linting of sources as an alternative to traditional RAG systems.

Provides stateful prompt optimization using research-backed techniques like APE and OPRO, learning from historical performance data via a vector database. It enables users to automatically refine prompts, retrieve high-performing examples, and track performance analytics through iterative feedback.

Serves an LLM-maintained markdown wiki to agents over MCP, providing tools for querying and navigating wiki pages without direct filesystem access.

An MCP server for a plain-markdown LLM wiki vault with YAML frontmatter and Obsidian-style wiki-links, enabling headless full-text search, note reading, backlink discovery, and safe append/create-only writing with path traversal protection and an immutable raw/ directory.

Community-driven library of tested prompts for AI agents, enabling search, retrieval, sharing, and rating of prompts.

Enables an LLM to autonomously maintain a Markdown-based wiki with YAML frontmatter, using hybrid BM25 and local CPU vector search for fully offline retrieval without external APIs or databases.

Enables natural language query and ingestion of wiki knowledge bases built from documents, powered by Claude Agent SDK skills.

An MCP server that provides AI agents with a governed wiki requiring human approval before any formal page update, combining structured knowledge management with safe, auditable writes.

A local-first MCP server that enables MCP hosts to use GLM-family LLM providers for knowledge consultation, reasoning, UI auditing, repository inspection, and approval-gated development assistance.