In Memoria
📇 🦀 🏠 🍎 🐧 🪟 - Persistent intelligence infrastructure for agentic development that gives AI coding assistants cumulative memory and pattern learning. Hybrid TypeScript/Rust implementation with local-first storage using SQLite + SurrealDB for semantic
What is In Memoria?
In Memoria is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to 📇 🦀 🏠 🍎 🐧 🪟 - persistent intelligence infrastructure for agentic development that gives ai coding assistants cumulative memory and pattern learning. hybrid typescript/rust implementation with lo...
📇 🦀 🏠 🍎 🐧 🪟 - Persistent intelligence infrastructure for agentic development that gives AI coding assistants cumulative memory and pattern learning. Hybrid TypeScript/Rust implementation with local-first storage using SQLite + SurrealDB for semantic
This server falls under the Knowledge & Memory and Coding Agents categories on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- 📇 🦀 🏠 🍎 🐧 🪟 - Persistent intelligence infrastructure for age
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx in-memoriaConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use In Memoria
In Memoria is a persistent intelligence infrastructure for AI coding assistants that gives them cumulative memory and pattern learning across development sessions. Built with a hybrid TypeScript/Rust implementation, it uses SQLite for structural metadata and SurrealDB with SurrealKV for persistent vector embeddings, with all processing handled locally via transformers.js so nothing leaves your machine. It exposes 13 specialized MCP tools covering codebase analysis, semantic code search, deep pattern learning, architectural decision tracking, developer profiling, and smart auto-learning — allowing coding agents to remember how you write code and make increasingly accurate suggestions over time.
Prerequisites
- Node.js 18 or later (for the npx-based MCP server)
- SurrealDB installed and running locally for persistent vector embeddings
- An MCP-compatible client such as Claude Desktop, Claude Code, or VS Code with GitHub Copilot
- Sufficient disk space for local embedding models (transformers.js downloads models on first run)
Install In Memoria globally
Install the in-memoria package globally with npm, or use npx for on-demand execution without a global install.
npm install -g in-memoriaStart SurrealDB for vector persistence
In Memoria uses SurrealDB with SurrealKV as its vector store backend. Start SurrealDB locally before launching the MCP server.
surreal start --log trace --user root --pass root surrealkv://data/in-memoria.dbAdd the server to Claude Desktop
Edit your Claude Desktop configuration file to register In Memoria as an MCP server.
Add via Claude Code CLI (alternative)
If you use Claude Code, you can register the server directly from the command line without editing JSON manually.
claude mcp add in-memoria -- npx in-memoria serverLet In Memoria analyze your codebase
After connecting, ask Claude to run the codebase analysis tool on your project. The first run will build the pattern index and download embedding models, which may take a few minutes.
Configure VS Code agents (optional)
VS Code users can configure the three built-in agents (explorer, feature implementation, code review) by creating an mcp.json in .vscode/ and accessing the agent definitions in .github/agents/.
In Memoria Examples
Client configuration
Add In Memoria to Claude Desktop. The server is started with npx and runs in stdio mode.
{
"mcpServers": {
"in-memoria": {
"command": "npx",
"args": ["in-memoria", "server"]
}
}
}Prompts to try
Ask your AI coding assistant to leverage In Memoria's pattern learning and semantic search capabilities.
- "Analyze this codebase and build a pattern index so you can make better suggestions"
- "Search the codebase for how I typically implement authentication middleware"
- "What files are most likely affected if I change the UserService interface?"
- "Show me a developer profile summarizing my coding patterns and preferred architecture"
- "Check health and tell me how many patterns you've learned so far"Troubleshooting In Memoria
Embedding generation is slow or fails on first run
transformers.js downloads embedding models on first use, which can take several minutes depending on your connection. Wait for the download to complete before running queries. The models are cached locally for subsequent runs.
SurrealDB connection error when starting the server
Ensure SurrealDB is running before starting In Memoria. Check that SurrealDB is accessible on its default port (8000) and that the credentials match. If SurrealDB is not installed, download it from surrealdb.com.
Pattern recommendations seem generic or inaccurate
In Memoria improves over time as it indexes more of your code. Run the codebase analysis tool on your main project directories and enable auto-learning so it captures patterns from your coding sessions. More indexed code leads to more personalized recommendations.
Frequently Asked Questions about In Memoria
What is In Memoria?
In Memoria is a Model Context Protocol (MCP) server that 📇 🦀 🏠 🍎 🐧 🪟 - persistent intelligence infrastructure for agentic development that gives ai coding assistants cumulative memory and pattern learning. hybrid typescript/rust implementation with local-first storage using sqlite + surrealdb for semantic It connects AI assistants to external tools and data sources through a standardized interface.
How do I install In Memoria?
Follow the installation instructions on the In Memoria GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with In Memoria?
In Memoria works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is In Memoria free to use?
Yes, In Memoria is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
In Memoria Alternatives — Similar Knowledge & Memory Servers
Looking for alternatives to In Memoria? Here are other popular knowledge & memory servers you can use with Claude, Cursor, and VS Code.
MemPalace
★ 52.6kA local AI memory system that stores all conversations verbatim and organizes them into navigable structures. It provides 19 MCP tools for AI assistants to search and retrieve past decisions, debugging sessions, and architecture debates automatically
Kratos
★ 25.7k🏛️ Memory System for AI Coding Tools - Never explain your codebase again. MCP server with perfect project isolation, 95.8% context accuracy, and the Four Pillars Framework.
Context Mode
★ 15.4kAn MCP server that preserves LLM context by intercepting large data outputs and returning only concise summaries or relevant sections. It enables efficient sandboxed code execution, file processing, and documentation indexing across multiple programm
Memu
★ 13.7kMemory for 24/7 proactive agents like OpenClaw.
MemOS
★ 9.3kMemOS (Memory Operating System) is a memory management operating system designed for AI applications. Its goal is: to enable your AI system to have long-term memory like a human, not only remembering what users have said but also actively invoking, u
Everos
★ 5.4kBuild, evaluate, and integrate long-term memory for self-evolving agents.
Browse More Knowledge & Memory MCP Servers
Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up In Memoria in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use In Memoria?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.