# llm-kosh

> llm-kosh — rastogivaibhav-llm-kosh. Use this tool when you need to securely store and manage AI model memory with durability and transparency. The llm-kosh cartridge solves problems of data integrity and auditability by providing inspectable and auditable memory storage. It is ideal for use cases requiring reliable and secure AI model memory management, with a read-only-by-default server interface for MCP-compatible AI clients.

Canonical page: https://skillsregistry.net/skills/rastogivaibhav-llm-kosh  
JSON: https://api.skillsregistry.net/v1/skills/rastogivaibhav-llm-kosh

## Description

A local-first memory cartridge for MCP-compatible AI clients, providing durable, inspectable, and auditable memory storage with a read-only-by-default MCP server.

## Trust

- **Trust score (0–1):** 0.29
- **Verification tier:** scanned
- **Last scanned:** 2026-08-29

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-08-29

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/u6631jiinx)
- **Repository:** <https://github.com/rastogivaibhav/llm-kosh>

## 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": "rastogivaibhav-llm-kosh"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/rastogivaibhav-llm-kosh` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/rastogivaibhav-llm-kosh/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