# persistent-memory-stack

> persistent-memory-stack — vshcherbukhin-persistent-memory-stack. Use this tool when you need to maintain context across sessions for AI agents like Claude, Codex, and MCP, and solve problems related to knowledge retention and semantic search. It provides a self-hosted memory solution with inputs like documents and knowledge graphs, and outputs like visualized knowledge and evidence-based results. Ideal for use cases requiring guided setup and shared knowledge management, with support for Docker, Ollama, and git integration.

Canonical page: https://skillsregistry.net/skills/vshcherbukhin-persistent-memory-stack  
JSON: https://api.skillsregistry.net/v1/skills/vshcherbukhin-persistent-memory-stack

## Description

Self-hosted memory for Claude, Codex, and MCP AI agents. Carry context across sessions with semantic search, a visual knowledge graph, document evidence, and optional shared knowledge. Guided Windows and macOS setup with Docker and Ollama.

## Trust

- **Trust score (0–1):** 0.57
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## 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/vshcherbukhin/persistent-memory-stack)

## 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": "vshcherbukhin-persistent-memory-stack"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/vshcherbukhin-persistent-memory-stack` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/vshcherbukhin-persistent-memory-stack/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
