In-Memoria

Overview

In Memoria is an MCP server built in Rust that learns from actual codebases and remembers across sessions. It analyzes patterns, architecture, and conventions to provide context-aware assistance to AI coding tools. The system combines Tree-sitter AST parsing for 12 languages with semantic analysis and pattern learning, storing data locally in SQLite and SurrealDB. It offers 13 specialized tools for AI assistants, including project blueprints, smart file routing, and pattern prediction.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

• analyze_codebase

  Analyze files/directories with concepts, patterns, complexity

  Try:Analyze the main components in this projectTry:What patterns exist in the utils directory?
• search_codebase

  Multi-mode search (semantic/text/pattern)

  Try:Find authentication-related codeTry:Search for database connection patterns
• learn_codebase_intelligence

  Deep learning to extract patterns and architecture

  Try:Learn from my current codebase structureTry:Extract all patterns from this project
• get_project_blueprint

  Instant project context with tech stack and entry points

  Try:What's the architecture of this project?Try:Show me the tech stack and main entry points
• get_semantic_insights

  Query learned concepts and relationships

  Try:How is authentication related to user management?Try:What components handle API routing?
• get_pattern_recommendations

  Get patterns with related files for consistency

  Try:What patterns should I follow for error handling?Try:Show me consistent patterns for API endpoints
• predict_coding_approach

  Implementation guidance with file routing

  Try:How would I implement a password reset feature?Try:Where should I add a new caching layer?
• get_developer_profile

  Access coding style and work context

  Try:What's my coding style preference?Try:What was I working on last session?
• contribute_insights

  Record architectural decisions

  Try:Record that we're using JWT for authenticationTry:Note our decision to use TypeScript for new features
• auto_learn_if_needed

  Smart auto-learning with staleness detection

  Try:Check if codebase needs updatingTry:Quickly analyze any new changes
• get_system_status

  Health check

  Try:Is the memory system working properly?Try:Check system health status
• get_intelligence_metrics

  Analytics on learned patterns

  Try:Show me what patterns have been learnedTry:How much of the codebase has been analyzed?

Comparable tools

Installation

# Install globally
npm install -g in-memoria

# Or use directly with npx
npx in-memoria --help

{
  "mcpServers": {
    "in-memoria": {
      "command": "npx",
      "args": ["in-memoria", "server"]
    }
  }
}

FAQ

What programming languages does In Memoria support?

Currently supports 12 languages: TypeScript, JavaScript, Python, PHP, Rust, Go, Java, C/C++, C#, Svelte, and SQL.

How does it store data?

Uses SQLite for structured data patterns and metadata, and SurrealDB with SurrealKV backend for persistent vector embeddings. Everything stays on your machine.

On Hacker News

Recent discussion from the developer community.

• Show HN: Built a memory layer that stops AI agents from forgetting everything▲ 13
  Story by pi_22by7 · 2025-08-19
• Show HN: In Memoria – AI memory layer for persistent context in coding tools▲ 2
  Story by pi_22by7 · 2025-08-31
• Show HN: In Memoria – MCP server that stops AI assistants from forgetting▲ 2💬 1
  Story by pi_22by7 · 2025-11-04

Compare In-Memoria with