# litopys

> Use this tool when you need to manage persistent graph-based memory for AI agents, solving problems of knowledge retention and retrieval through a simple markdown-based interface. It accepts plain text inputs and outputs via stdio and HTTP/SSE transports, allowing for efficient storage and querying of typed nodes and relations. Ideal for use cases requiring flexible and scalable knowledge management, such as chatbots, virtual assistants, and other AI applications.

Canonical page: https://skillsregistry.net/skills/litopys-dev-litopys  
JSON: https://api.skillsregistry.net/v1/skills/litopys-dev-litopys

## Description

Persistent graph-based memory for AI agents, stored as plain markdown — no vector DB. Typed nodes and 11 relation types via 5 MCP tools (search, get, create, link, related), stdio and HTTP/SSE transports.

## Trust

- **Trust score (0–1):** 0.99
- **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/qz7azkkmgw)
- **Repository:** <https://github.com/litopys-dev/litopys>

## 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": "litopys-dev-litopys"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/litopys-dev-litopys` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/litopys-dev-litopys/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