# Krusch Memory

> Use this tool when you need to provide AI agents with persistent memory across sessions, solving problems of knowledge retention and continuity. It takes in vector embeddings as input and outputs a semantic memory that naturally ages over time, with support for both single-developer and high-throughput environments. Ideal for use cases requiring session continuity and knowledge retention, such as conversational AI and multi-step workflows.

Canonical page: https://skillsregistry.net/skills/krusch-memory  
JSON: https://api.skillsregistry.net/v1/skills/krusch-memory

## Description

Krusch Memory provides AI agents with persistent semantic memory across sessions using vector embeddings via local Ollama. Supports SQLite for single-developer use and PostgreSQL for high-throughput agent swarms, with exponential temporal decay for natural memory aging and session continuity.

## Trust

- **Trust score (0–1):** 0.64
- **Verification tier:** scanned
- **Last scanned:** 2026-09-01

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-09-01

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/krusch-memory)
- **Repository:** <https://github.com/kruschdev/krusch_memory_mcp>

## 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": "krusch-memory"
    }
  }
}
```

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