Yantrikdb

v1.0.0Knowledge & Memorystable

Cognitive memory database for AI agents — consolidates duplicates, detects contradictions, fades stale memories via temporal decay. Rust, AGPL, ships as library / MCP server / HTTP cluster.

agent-memoryai-agentsanthropicclaude-codeclustering
Share:
147
Stars
0
Downloads
0
Weekly
0/5

What is Yantrikdb?

Yantrikdb is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to cognitive memory database for ai agents — consolidates duplicates, detects contradictions, fades stale memories via temporal decay. rust, agpl, ships as library / mcp server / http cluster.

Cognitive memory database for AI agents — consolidates duplicates, detects contradictions, fades stale memories via temporal decay. Rust, AGPL, ships as library / MCP server / HTTP cluster.

This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Cognitive memory database for AI agents — consolidates dupli

Use Cases

Store persistent memories for AI agents
Detect contradictions and consolidate duplicates
Apply temporal decay to stale information
yantrikos

Maintainer

LicenseAGPL-3.0
Languagerust
Versionv1.0.0
UpdatedMay 21, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx yantrikdb

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Yantrikdb

YantrikDB is a cognitive memory database designed specifically for AI agents, implemented in Rust and available as a Python MCP server, an embedded library, and an HTTP cluster. It stores agent memories with semantic embeddings (HNSW index), automatically consolidates near-duplicate memories, detects and flags contradictions between stored facts, and applies configurable temporal decay so stale information loses relevance over time. This gives AI agents like Claude a persistent, self-organizing long-term memory that grows more coherent with use rather than accumulating noise.

Prerequisites

  • Python 3.9+ for the MCP server (yantrikdb-mcp package) or Rust toolchain for the embedded library
  • pip for installing yantrikdb-mcp
  • An MCP-compatible client such as Claude Desktop, Claude Code CLI, Cursor, or Windsurf
  • Optional: Docker for running the distributed HTTP cluster mode
1

Install the yantrikdb-mcp Python package

Install the MCP server package from PyPI. This installs the yantrikdb-mcp command that your MCP client will invoke.

pip install yantrikdb-mcp
2

Add yantrikdb to your MCP client config (local SQLite mode)

The simplest configuration runs yantrikdb-mcp locally with a SQLite backend. The database is auto-initialized at ~/.yantrikdb/memory.db on first run. No additional environment variables are required for local mode.

{
  "mcpServers": {
    "yantrikdb": {
      "command": "yantrikdb-mcp"
    }
  }
}
3

Restart your MCP client

Restart Claude Desktop or your chosen MCP client. YantrikDB exposes 15 tools including remember, recall, forget, correct, think, conflict, temporal, and others for memory management.

4

Optionally configure cluster mode

For multi-node deployments, start the Docker container and configure the MCP server to connect to the remote cluster with authentication.

# Start the YantrikDB server node
docker run -p 7438:7438 ghcr.io/yantrikos/yantrikdb:latest
5

Configure cluster connection (optional)

Update your MCP config to point to a remote YantrikDB cluster using YANTRIKDB_SERVER_URL and YANTRIKDB_TOKEN environment variables.

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

Yantrikdb Examples

Client configuration

Minimal claude_desktop_config.json for local YantrikDB with SQLite. No credentials needed — the database is created automatically.

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

Prompts to try

Prompts demonstrating how to use YantrikDB's memory capabilities through an AI assistant.

- "Remember that Alice is the engineering lead and her timezone is UTC+5:30"
- "What do you know about Alice?"
- "I told you earlier that Bob is the CEO — please correct that, it's actually Carol"
- "Check for any conflicting facts in your memory about the team structure"
- "Forget everything you stored about the old project 'Phoenix'"
- "Show memory stats — how many entries are stored and what is the average relevance score?"

Troubleshooting Yantrikdb

yantrikdb-mcp command not found after pip install

Ensure the Python scripts directory is in your PATH. On macOS/Linux, run `export PATH=$PATH:$(python3 -m site --user-base)/bin`. On Windows, add the Python Scripts folder to the PATH environment variable.

Contradiction detection not triggering for conflicting facts

Contradictions are detected when you call the `think` tool (or Claude invokes it during a session). Explicitly ask: 'Run the think process to consolidate memories and find contradictions.' The tool consolidates duplicates and surfaces conflicts.

Memories from previous sessions are not recalled

Confirm the database path is stable. In local SQLite mode, the default is ~/.yantrikdb/memory.db. If you run yantrikdb-mcp from different working directories, add an explicit DB_PATH env var pointing to a fixed absolute path.

Frequently Asked Questions about Yantrikdb

What is Yantrikdb?

Yantrikdb is a Model Context Protocol (MCP) server that cognitive memory database for ai agents — consolidates duplicates, detects contradictions, fades stale memories via temporal decay. rust, agpl, ships as library / mcp server / http cluster. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Yantrikdb?

Follow the installation instructions on the Yantrikdb GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Yantrikdb?

Yantrikdb works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Yantrikdb free to use?

Yes, Yantrikdb is open source and available under the AGPL-3.0 license. You can use it freely in both personal and commercial projects.

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.

Quick Config Preview

{ "mcpServers": { "yantrikdb": { "command": "npx", "args": ["-y", "yantrikdb"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Yantrikdb?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides