archiledger

Overview

Archiledger provides a knowledge graph-based memory system for AI assistants, implementing the Model Context Protocol to enable persistent memory across conversations. It offers both low-level manual control tools and high-level AI-powered memory management capabilities through its Agentic Memory module. The system uses an embedded graph database (LadybugDB) and supports vector search for semantic similarity retrieval of notes, with features like tagging, linking, and graph traversal.

Try asking AI

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

• create_notes

  Create one or more memory notes with content, keywords, tags, and optional links

  Try:Create a new note about my project architectureTry:Add a note with links to related requirements
• get_note

  Retrieve a specific note by ID (increments retrieval counter)

  Try:Get the note with ID 12345Try:Show me the note about authentication
• get_notes_by_tag

  Find all notes with a given tag

  Try:Find all notes tagged as 'bug'Try:Show me all notes with the 'architecture' tag
• delete_notes

  Delete notes by their IDs, including associated links and embeddings

  Try:Delete note ID 12345Try:Remove outdated notes about deprecated features
• add_links

  Add typed links between notes with context

  Try:Link note 123 to note 456 with a 'DEPENDS_ON' relationshipTry:Connect these two notes as 'RELATED_TO'
• delete_links

  Remove typed links between notes

  Try:Remove the link between note 123 and note 456Try:Delete all CONTRADICTS links from this note
• read_graph

  Read the entire knowledge graph (all notes and links)

  Try:Show me the complete knowledge graphTry:Export all nodes and relationships
• get_linked_notes

  Find all notes directly connected to a given note

  Try:Show all notes connected to ID 123Try:What notes are linked to this requirement?
• get_all_tags

  List all unique tags currently used across notes

  Try:Show me all tags in the knowledge graphTry:What categories are used to organize notes?
• search_notes

  Semantic similarity search with temperature scaling and threshold filtering

  Try:Find notes similar to 'user authentication'Try:Search for content about microservices architecture
• memory_vector_search

  Perform semantic similarity search across memory notes

  Try:Find notes similar to 'payment processing'Try:Search for information about database migrations
• agentic_memory_write

  Store content with automatic AI classification, tagging, and link generation

  Try:Save this note about API design with automatic categorizationTry:Store this information with AI-generated links to related concepts

Comparable tools

Installation

mvn clean package

java -jar mcp/target/archiledger-server-1.0.0-SNAPSHOT.jar

java -Dladybugdb.data-path=./archiledger.lbdb 
     -jar mcp/target/archiledger-server-1.0.0-SNAPSHOT.jar

{
  "mcpServers": {
    "archiledger": {
      "command": "java",
      "args": ["-jar", "mcp/target/archiledger-server-1.0.0-SNAPSHOT.jar"],
      "env": {
        "LADYBUGDB_DATA_PATH": "./archiledger.lbdb"
      }
    }
  }
}

FAQ

Is Archiledger suitable for production use?

No, the README explicitly states this server implements no authentication and uses an embedded graph database designed for local development only. It is not recommended for production.

What is the difference between low-level and agentic memory MCP servers?

The low-level MCP server provides direct tools for manual control over memory operations, while the agentic memory MCP server uses AI to automatically handle classification, tagging, and linking between notes with minimal manual management.

Compare archiledger with