Enterprise DNAEnterprise DNA
MMCP ServersMemorylow

afairai/afair

by Various

The open-source, self-organizing memory for all your AI tools. Single-tenant, yours, over MCP.

MCP

afairai/afair

Added 8 Sept 2026

#agpl#ai-agents#ai-memory#llm#mcp#mcp-server#memory#model-context-protocol
Catalogue record, not a reviewed recommendation. This record can include automatically collected descriptions and setup details. Confirm important claims with the original source. Explore source-reviewed tools.

Overview

afairai/afair is an open-source Python project that provides a self-organizing memory layer for AI tools. It is single-tenant and designed to be self-hosted, exposing memory over the Model Context Protocol (MCP).

Best for

Best for
Developers who want a self-hosted, MCP-based memory layer for their AI tools.

Use cases

  • Give AI assistants persistent, self-organizing memory
  • Share context across multiple AI tools via MCP
  • Self-host a private memory server for AI workflows

How to use

Clients listed in this record (not verified here)

Claude Code, Cursor, Windsurf, VS Code, ChatGPT

Notes

6 stars on GitHub. Last updated 2026-09-07. Licensed AGPL-3.0.

Pros

  • Open source and self-hostable
  • Single-tenant design keeps data private
  • Uses the standard MCP interface

Cons

  • Very early stage with few stars (6)
  • Limited documentation and community support
  • Requires Python environment and MCP setup

Pairs with

Other entries in the index that connect to this one. Click through to see the chain.

Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.