# Dense Mem

> Use this tool when you need to manage and retrieve complex AI agent memory data, solving problems of knowledge graph management, data provenance, and conflict detection. It accepts various data inputs and outputs typed claims, evidence, and embeddings, utilizing PostgreSQL and Neo4j databases. Ideal for use cases requiring robust, self-hosted memory management for AI agents, enabling efficient recall and conflict resolution.

Canonical page: https://skillsregistry.net/skills/markhuangai-dense-mem  
JSON: https://api.skillsregistry.net/v1/skills/markhuangai-dense-mem

## Description

About
Self-hosted AI agent memory server with MCP, evidence provenance, typed claims, conflict detection, embeddings, recall, PostgreSQL, and Neo4j.

## Trust

- **Trust score (0–1):** 0.69
- **Verification tier:** scanned
- **Last scanned:** 2026-08-31

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-08-31

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/j0udkgu1nu)
- **Repository:** <https://github.com/markhuangai/dense-mem>

## 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": "markhuangai-dense-mem"
    }
  }
}
```

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