# mneme

> mneme — slow-stack-mneme. Use this tool when you need to retain information across sessions, enabling seamless continuity and private knowledge management. Mneme solves the problem of lost context and forgotten insights by providing a cross-session memory for DeepSeek Harness, auto-consolidating information offline. It offers a visualized memory panel as output, accepting git inputs and operating in the context of AI model training and development.

Canonical page: https://skillsregistry.net/skills/slow-stack-mneme  
JSON: https://api.skillsregistry.net/v1/skills/slow-stack-mneme

## Description

🧠 The memory that dreams — cross-session memory for DeepSeek Harness. Offline & private, auto-consolidates in its sleep (autoDream), visualized in a memory panel.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/slow-stack/mneme)

## 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": "slow-stack-mneme"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/slow-stack-mneme` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/slow-stack-mneme/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