memora

Overview

Memora is a comprehensive MCP server designed to give AI agents persistent memory capabilities. It provides semantic storage with SQLite or cloud databases, supports vector embeddings for advanced search, and maintains knowledge graphs with interactive visualization. The server offers features like memory deduplication, document storage with fragment trees, and a chat interface for querying memories. It supports multiple embedding backends including OpenAI, sentence-transformers, and TF-IDF, with flexible configuration options for different deployment scenarios.

Try asking AI

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

• memory_create

  Create a new memory with content, tags, and optional metadata

  Try:Create a new memory about project deadlinesTry:Save this meeting note as a memory
• memory_update

  Update an existing memory with new content or metadata

  Try:Update memory #12 with new informationTry:Change the tags on memory #5
• memory_create_batch

  Create multiple memories at once

  Try:Batch create these notes as memoriesTry:Import these items as memories
• memory_search

  Search memories using semantic search, filters, and full-text queries

  Try:Find memories about product featuresTry:Search for memories from last week
• memory_delete

  Delete a memory or set of memories

  Try:Delete memory #42Try:Remove all memories with tag 'obsolete'
• memory_rebuild_embeddings

  Rebuild embeddings for all memories after changing embedding models

  Try:Rebuild all embeddings with new modelTry:Update memory vectors
• memory_rebuild_crossrefs

  Rebuild cross-references between memories based on similarity

  Try:Update memory connectionsTry:Rebuild knowledge graph links
• memory_chat

  Chat with memories using RAG-powered responses with tool calling

  Try:What do I know about customer feedback?Try:Summarize my project memories

Comparable tools

Installation

pip install git+https://github.com/agentic-box/memora.git

{
  "mcpServers": {
    "memora": {
      "command": "memora-server",
      "args": [],
      "env": {
        "MEMORA_DB_PATH": "~/.local/share/memora/memories.db",
        "MEMORA_ALLOW_ANY_TAG": "1"
      }
    }
  }
}

FAQ

What databases does Memora support?

Memora supports local SQLite databases and cloud storage through Cloudflare D1 or S3/R2 with optional encryption and compression.

Can I use Memora offline?

Yes, you can use local embeddings with TF-IDF or sentence-transformers to run completely offline without requiring API calls.

Compare memora with