# Munin AI Memory

> Use this tool when you need to efficiently manage and retrieve knowledge for AI agents, solving problems of information overload and context switching across multiple projects. Munin AI Memory provides a high-performance memory layer with multi-project support, automatic knowledge graph building, and fast search capabilities. It is ideal for use cases requiring rapid and semantic information retrieval, with inputs including context data and outputs featuring relevant knowledge graph results.

Canonical page: https://skillsregistry.net/skills/3d-era-munin-for-agents  
JSON: https://api.skillsregistry.net/v1/skills/3d-era-munin-for-agents

## Description

Munin is a high-performance, pragmatic memory layer for AI agents (Cursor, Claude Code, OpenClaw, Gemini CLI,...). Unlike other solutions, Munin focuses on developer productivity with:

* Multi-Project Support: Isolate memories into separate "brains" (Context Cores).
* GraphRAG: Automatically builds a knowledge graph from your context.
* Sub-200ms Search: Blazing fast Hybrid & Semantic

## Trust

- **Trust score (0–1):** 0.83
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-19

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/iijqu9fe2d)
- **Repository:** <https://github.com/3d-era/munin-for-agents>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "3d-era-munin-for-agents"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/3d-era-munin-for-agents` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/3d-era-munin-for-agents/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt
