# mem-graph

> mem-graph — govanai-mem-graph. Use this tool when you need to enhance language model performance with persistent memory capabilities, solving problems of knowledge retention and recall in applications such as question answering and text generation. The mem-graph tool takes in text inputs and outputs linked knowledge graphs, utilizing features like wikilinks and BM25 auto-linking to create a relational memory structure. It is particularly useful in contexts where maintaining a knowledge base across multiple interactions is crucial.

Canonical page: https://skillsregistry.net/skills/govanai-mem-graph  
JSON: https://api.skillsregistry.net/v1/skills/govanai-mem-graph

## Description

Graph-relational memory MCP server for persistent LLM memory, featuring wikilinks, BM25 auto-linking, spreading activation, and synaptic decay across five memory layers.

## Trust

- **Trust score (0–1):** 0.68
- **Verification tier:** scanned
- **Last scanned:** 2026-08-30

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-08-30

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/gacq2z5glm)
- **Repository:** <https://github.com/GoVanAI/mem-graph>

## 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": "govanai-mem-graph"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/govanai-mem-graph` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/govanai-mem-graph/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