Skip to content
MCP server

Kagura Memory Cloud

Self-hosted MCP memory server with hybrid search and a learning memory graph

Pricing
Open source
Platforms
self-hosted, Web, API
Runs
Remotely
Version
0.167.0
Listing updated
3 days ago

About Kagura Memory Cloud

Kagura Memory Cloud is an open-source MCP server for knowledge and memory. It runs as a hosted remote server, so there is nothing to install locally.

Kagura Memory Cloud stores what an assistant learns in PostgreSQL and Qdrant, then retrieves it with semantic and BM25 search plus optional reranking. Its distinguishing piece is a graph that strengthens links between memories each time they are retrieved together, so an explore() call can surface related notes you did not search for.

Memories sit in contexts inside team workspaces with owner, admin, member and viewer roles, each memory carrying summary, context and content layers. A sleep-maintenance job consolidates in the background. The README also lists file storage, secrets handling and an agent registry in preview.

It works with Claude, ChatGPT, Gemini and other MCP clients, and a Python SDK is included. Embeddings can come from OpenAI or a local Ollama or vLLM.

Install

Run in a terminal

claude mcp add --transport http memory-cloud https://memory.kagura-ai.com/mcp

Add to Settings → Connectors → Add custom connector

https://memory.kagura-ai.com/mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "memory-cloud": {
      "url": "https://memory.kagura-ai.com/mcp"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "memory-cloud": {
      "type": "http",
      "url": "https://memory.kagura-ai.com/mcp"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "memory-cloud": {
      "serverUrl": "https://memory.kagura-ai.com/mcp"
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "memory-cloud": {
      "type": "http",
      "url": "https://memory.kagura-ai.com/mcp"
    }
  }
}

Tools this server provides (2)

Taken from the project documentation; the running server may differ.

remember
Store a memory
explore
Traverse the memory graph

What it does

Hybrid retrieval
Semantic plus keyword search with optional reranking.
Learning graph
Hebbian links form between memories used together.
Team workspaces
Contexts and role-based access.
Sleep maintenance
Background consolidation of memories.
Local embeddings
Ollama or vLLM instead of OpenAI.
Web dashboard
Next.js UI for contexts and members.

Good for

  • Give an assistant memory across conversations
  • Share project knowledge across a team
  • Discover related notes through graph exploration
  • Keep memory private on your own infrastructure

Pricing

Open source

Prices change. Check memory.kagura-ai.com before you buy.

Kagura Memory Cloud FAQ

Is it self-hosted?

Yes, the README presents it as a self-hosted open source platform.

Which stores does it use?

PostgreSQL and Qdrant, with an optional file store.

Can embeddings stay local?

Yes, through Ollama or vLLM.

Which clients work?

Claude, ChatGPT, Gemini and other MCP clients.

Is Kagura Memory Cloud free?

Yes. Kagura Memory Cloud is open source, so you can use and self-host it for free.

How do I add Kagura Memory Cloud to Claude Code?

Run this command in your terminal: claude mcp add --transport http memory-cloud https://memory.kagura-ai.com/mcp

What are the best alternatives to Kagura Memory Cloud?

The closest alternatives to Kagura Memory Cloud are Codebase Memory, XERJ, Claude Code Ultimate Guide, Nautilus Compass Memory and note1.

Alternatives to Kagura Memory Cloud

  1. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  2. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  3. MCP server for searching the Claude Code Ultimate Guide from any MCP client

    Runs locally
    • Open source
    • 6.5K GitHub stars
    • AI models and LLM tooling
  4. Local-first long-term memory layer for AI agents, served over MCP

    Not checked yet
    • 5 tools
    • Remote
    • Open source
    • 1.3K GitHub stars
    • Knowledge and memory
  5. note1

    MCP server

    MCP server giving AI assistants search and summaries across your note1 meetings

    • 4 tools
    • Remote
    • Free trial
    • 1 GitHub star
    • Productivity