What problem does In Memoria solve?
Every AI coding session starts from scratch, forcing users to repeatedly explain conventions, architecture, and decisions. In Memoria eliminates this "session amnesia" by remembering across sessions.

@pi22by7
Basic information
Persistent codebase intelligence that gives agents memory across sessions.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"in-memoria": {
"command": "npx",
"args": [
"in-memoria",
"server"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
Fetch the live tool list by running this server in a temporary sandbox using the button above.
In Memoria is an MCP (Model Context Protocol) server that gives AI coding assistants persistent memory across sessions by learning from your codebase's patterns, architecture, conventions, and decisions.
Install the npm package in-memoria and configure it as an MCP server for your AI coding assistant (e.g., Claude, Copilot, Cursor). Once configured, the server automatically learns from your codebase and provides context to the AI during sessions.
Every AI coding session starts from scratch, forcing users to repeatedly explain conventions, architecture, and decisions. In Memoria eliminates this "session amnesia" by remembering across sessions.
It acts as an MCP server that learns from your actual codebase—patterns, architecture, conventions, and decisions—and stores them persistently so AI assistants can query that knowledge on demand.
In Memoria works with any AI assistant that supports the Model Context Protocol, such as Claude, GitHub Copilot, and Cursor.
In Memoria is a Node.js package available on npm. You need a Node.js runtime and an MCP-compatible AI coding assistant host.
It learns patterns, architecture, conventions, and decisions from your codebase, including what works, what was rejected, and why—so the AI doesn't repeat mistakes.
YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.
PickFu MCP is a Model Context Protocol (MCP) server that connects AI assistants, developers, marketers, product managers, and AI agents to PickFu's consumer research platform. It enables users to create surveys, conduct

Your AI assistant logs your meals and workouts, then plans your week from what you did. iPhone, Android and Garmin.

Yuppsy MCP: build and publish real estate websites from your AI assistant. Yuppsy lets your AI assistant create live websites for real estate agents and individual property listings. You don't need a designer or any code
Comments