Yantrikdb
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.
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
Maintainer
Works with
Installation
Manual Installation
npx yantrikdbConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
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
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-mcpAdd 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"
}
}
}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.
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:latestConfigure 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.
Yantrikdb Alternatives — Similar Knowledge & Memory Servers
Looking for alternatives to Yantrikdb? Here are other popular knowledge & memory servers you can use with Claude, Cursor, and VS Code.
MemPalace
★ 52.6kA local AI memory system that stores all conversations verbatim and organizes them into navigable structures. It provides 19 MCP tools for AI assistants to search and retrieve past decisions, debugging sessions, and architecture debates automatically
Kratos
★ 25.7k🏛️ Memory System for AI Coding Tools - Never explain your codebase again. MCP server with perfect project isolation, 95.8% context accuracy, and the Four Pillars Framework.
Context Mode
★ 15.4kAn MCP server that preserves LLM context by intercepting large data outputs and returning only concise summaries or relevant sections. It enables efficient sandboxed code execution, file processing, and documentation indexing across multiple programm
Memu
★ 13.7kMemory for 24/7 proactive agents like OpenClaw.
MemOS
★ 9.3kMemOS (Memory Operating System) is a memory management operating system designed for AI applications. Its goal is: to enable your AI system to have long-term memory like a human, not only remembering what users have said but also actively invoking, u
Everos
★ 5.4kBuild, evaluate, and integrate long-term memory for self-evolving agents.
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.
Set Up Yantrikdb in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
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.