Happy slice of mcp pizzaMCP.pizza
mnemo

mnemo

MCP.Pizza Chef: MnemoAI

Mnemo is a code library rather than something you switch on inside a chat app: a developer writes Python that wires an assistant up to files, web pages, and search tools. There is no ready-made setup for Claude Desktop or Cursor. Treat it as a stalled project — the last change landed in May 2025, and the install command in its instructions actually downloads an unrelated package of the same name from Python's public catalog.

Unmaintained · no code changes since May 2025
Coding

Use This MCP client To

Build a Python assistant that reads local files and web pages Chain several small assistants together inside one script Give an assistant a memory of what it did earlier Study working example code for wiring assistants to outside tools

README

Mnemo

Mnemo Logo

Composable AI Agents & Realtime Data Interfaces Powered by Model Context Protocol CA:0x7bfdb47ab24b6cb7017865431179e150d4bc4444

Overview

Mnemo is a modular agent framework built on top of the Model Context Protocol (MCP), designed to orchestrate Retrieval-Augmented Generation (RAG) pipelines and intelligent agent workflows using real-time, pluggable data services.

Mnemo integrates two emerging standards:

  1. Model Context Protocol (MCP): Enables real-time, protocol-based interaction with external tools, data streams, and services via MCP servers.
  2. Composable Agent Architecture: Inspired by effective production patterns, Mnemo allows developers to build, chain, and orchestrate modular agents across tasks and domains.

Why Mnemo?

Mnemo is purpose-built to:

  • 🔌 Plug into any MCP-compliant data or tool service
  • 🔍 Enable real-time RAG pipelines with multi-modal inputs
  • 🧠 Build chainable, domain-specific agents with memory, logic and persistence
  • 🧩 Expose agents as MCP clients or servers, enabling two-way integration

Whether you're building autonomous workflows, human-in-the-loop systems, or live decision agents powered by streaming on-chain or enterprise data—Mnemo provides the infrastructure layer to deploy them quickly.

Features

  • ⚙️ MCP-Oriented Design: Fully compatible with MCP server/client pattern; enables hot-swappable data interfaces and execution environments.
  • 📚 RAG-Native Agent Workflows: First-class support for Retrieval-Augmented Generation with vector store and unstructured data integration.
  • 🤖 Composable Agent Engine: Build modular agents that orchestrate, call tools, persist memory, and coordinate via workflows.
  • 🪝 Real-Time Tool Calls: Automatically fetch, retrieve, and operate on data exposed by any MCP-compliant service (e.g., filesystem, fetch, email, SQL, vector DBs).
  • 🧪 Multi-Agent Orchestration: Supports cooperative task planning, evaluation agents, and Swarm-style distributed processing.

Installation

We recommend using uv to manage your Python environments:

mnemo FAQ

Is this still maintained?
No. The last code change was in May 2025 and nothing has moved since. The project does not name a successor.
Can I use it inside Claude Desktop or ChatGPT?
No. It is a Python library for developers, not something you add to a chat app.
Does the published install command work?
Not as written. Installing the name 'mnemo' from Python's public catalog gets an unrelated project by a different author.
Do I need a paid key?
Yes. The examples expect you to paste your own model provider credentials into a secrets file.
Can I use this to summarize a web page?
Yes — the sample agent reads a link and writes a summary, but you have to run the Python code yourself.
How hard is setup?
Developer-level. You clone the repository, manage a Python environment, and write code to get anything out of it.