# Kagura Memory Cloud

An MCP server with adaptive memory that builds a neural graph of connections and learns from every search your agent makes.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 12
- Author: kagura-ai
- License: Apache-2.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/kagura-ai/memory-cloud
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/mcp/kagura-memory-cloud

## What it does

The server stores knowledge across agent sessions and links entries through a Hebbian neural graph: each `recall()` call strengthens edges between co-retrieved memories. Search runs in two modes — `recall()` for precise hybrid retrieval (semantic plus BM25) and `explore()` for graph traversal.

Each memory has three layers: summary, context, and full content. The agent writes via `remember()`, the server indexes automatically. Ships with 72 MCP tools: memory operations, contexts, tags, R2 file storage, analyses, secrets, and sleep maintenance scheduler.

Works with OpenAI or locally via Ollama and vLLM. Requires Python 3.11 or higher, Node.js 20 or higher. The `./setup.sh` script gets the server running in five minutes. Architecture uses workspaces with contexts and RBAC, memory isolation per team.

## Requirements
- Remote server: `https://memory.kagura-ai.com/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http memory-cloud https://memory.kagura-ai.com/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add kagura-memory-cloud --url https://memory.kagura-ai.com/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "kagura-memory-cloud": {
            "url": "https://memory.kagura-ai.com/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "kagura-memory-cloud": {
            "type": "http",
            "url": "https://memory.kagura-ai.com/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http kagura-memory-cloud https://memory.kagura-ai.com/mcp
```

## When to use it
- persist agent knowledge across conversations and projects
- surface connections between entries the agent retrieved at different times
- give the agent hybrid search — semantic and keyword together
- organize team memory with access control and context isolation
- run embeddings and reranking locally without external APIs

## Example prompts
- Store the project context: architecture is FastAPI microservices, database is PostgreSQL, queues are Redis.
- Find everything I saved about Qdrant configuration.
- Show memories related to the last auth module bug.

## Similar
- [REA](https://affpapa.org/en/nevibecode/mcp/rea.md) — MCP server · ★ 386989
- [GitHub](https://affpapa.org/en/nevibecode/mcp/github.md) — MCP server · ★ 33918
- [Netdata](https://affpapa.org/en/nevibecode/mcp/netdata.md) — MCP server · ★ 81115
- [browser-use](https://affpapa.org/en/nevibecode/mcp/browser-use.md) — MCP server · ★ 119160
- [Codebase Memory](https://affpapa.org/en/nevibecode/mcp/codebase-memory.md) — MCP server · ★ 47392
- [mcp-server](https://affpapa.org/en/nevibecode/mcp/mcp-server.md) — MCP server · ★ 43872

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md