MCP Catalogs
Homeyantrikdb-server screenshot

yantrikdb-server

by yantrikos·143·Score 50

Cognitive memory database for AI agents that consolidates duplicates, detects contradictions, and fades stale memories via temporal decay.

ai-llmknowledge-graphdatabase
9
Forks
9
Open issues
this month
Last commit
2d ago
Indexed

Overview

YantrikDB is a unique cognitive memory engine that manages memories rather than just storing them. Unlike traditional vector databases, it implements three key features: forgetting (via temporal decay with configurable half-life), consolidation (collapsing similar memories into canonical forms), and conflict detection (identifying contradictions between memories). It offers significant token savings compared to file-based memory systems - up to 99.9% at 5,000 memories while improving recall precision. The system can be deployed as a library, HTTP server, or MCP server, with proactive triggers that surface what needs attention rather than requiring agents to constantly query.

Try asking AI

After installing, here are 7 things you can ask your AI assistant:

you:Long-term memory management for AI agents to avoid context window overflow
you:Conflict detection and resolution in multi-conversation AI systems
you:Personalized AI assistants that learn user preferences over time
you:Knowledge consolidation for enterprise document management systems
you:How does YantrikDB differ from vector databases like Pinecone or Weaviate?
you:Can I use YantrikDB without an internet connection?
you:How much memory does YantrikDB use at scale?

When to choose this

Choose YantrikDB when building AI agents that need sophisticated memory management beyond simple retrieval, especially when dealing with long-term memory, conflict detection, or temporal relevance.

When NOT to choose this

Not ideal if you need simple key-value storage without cognitive features; AGPL license may be problematic for commercial use without compliance.

Tools this server exposes

12 tools extracted from the README
  • remember

    Store new memories with text, importance, and temporal decay

  • recall

    Retrieve relevant memories based on query and context

  • forget

    Remove specific memories from the database

  • correct

    Update or correct existing memories

  • think

    Perform cognitive operations: consolidate memories, detect contradictions

  • memory

    Access or manipulate memory structures

  • trigger

    Get proactive insights from memory system

  • graph

    Access the knowledge graph of entities and relationships

  • category

    Organize or query memories by categories

  • conflict

    List or resolve contradictions in stored memories

  • session

    Manage session-specific memories and context

  • temporal

    Query memories based on time: stale, upcoming, or time-bound

Comparable tools

mem0-mcpchromadbvectordbredis-mcp

Installation

Quick Start with MCP

pip install yantrikdb-mcp

Add to your MCP client config (typically ~/.claude.json or .mcp.json):

{
  "mcpServers": {
    "yantrikdb": {
      "command": "yantrikdb-mcp"
    }
  }
}

For shared memory across machines:

{
  "mcpServers": {
    "yantrikdb": {
      "command": "yantrikdb-mcp",
      "env": {
        "YANTRIKDB_SERVER_URL": "http://node1:7438,http://node2:7438",
        "YANTRIKDB_TOKEN": "ydb_your_database_token"
      }
    }
  }
}

As a Network Server

docker run -p 7438:7438 ghcr.io/yantrikos/yantrikdb:latest

FAQ

How does YantrikDB differ from vector databases like Pinecone or Weaviate?
Vector databases focus on nearest-neighbor lookup but lack memory management features. YantrikDB implements temporal decay, consolidation of similar memories, and conflict detection - making it a cognitive memory system rather than just a storage layer.
Can I use YantrikDB without an internet connection?
Yes, YantrikDB can run as an embedded library that works offline with a local SQLite file. It only requires network connectivity if you use the clustered deployment option.
How much memory does YantrikDB use at scale?
Despite storing thousands of memories, YantrikDB maintains a constant ~70 tokens per query, regardless of memory count. This contrasts with file-based systems that grow linearly with memory count.

On Hacker News

Recent discussion from the developer community.

Compare yantrikdb-server with

GitHub →

Last updated · Auto-generated from public README + GitHub signals.