Kagura Memory Cloud — Claude Code MCP server: adaptive agent memory
An MCP server with adaptive memory that builds a neural graph of connections and learns from every search your agent makes.
claude mcp add --transport http memory-cloud https://memory.kagura-ai.com/mcpWhat Kagura Memory Cloud 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.
What it helps with
- 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 for the agent
- 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.
How to install Kagura Memory Cloud
Platform CLI: remote server
claude mcp add --transport http memory-cloud https://memory.kagura-ai.com/mcpPlatform CLI: remote server
codex mcp add kagura-memory-cloud --url https://memory.kagura-ai.com/mcpConfig file
{
"mcpServers": {
"kagura-memory-cloud": {
"url": "https://memory.kagura-ai.com/mcp"
}
}
}Config file
{
"servers": {
"kagura-memory-cloud": {
"type": "http",
"url": "https://memory.kagura-ai.com/mcp"
}
}
}Platform CLI: remote server
gemini mcp add -t http kagura-memory-cloud https://memory.kagura-ai.com/mcpStep by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about Kagura Memory Cloud
How do I install Kagura Memory Cloud in Claude Code?
Run claude mcp add --transport http memory-cloud https://memory.kagura-ai.com/mcp. The server will be added to your MCP configuration and the agent will have access to memory tools.
What does Kagura Memory Cloud do?
It gives the agent persistent memory that learns: entries are linked through a neural graph, and every search strengthens edges between co-retrieved memories. Search works through a hybrid index combining semantic and BM25 retrieval.
Can I run embeddings locally?
Yes. The server supports Ollama and vLLM for embeddings and reranking — runs without external APIs, locally and at no cost.
