# O_Owl

> O_Owl — smcozart-o-owl. Use this tool when you need to enhance AI agents with advanced cognitive memory capabilities, solving problems related to knowledge retention and retrieval. O_Owl provides a robust interface with 5 memory types, composite weight scoring, and a knowledge graph, accepting various data inputs and outputting weighted knowledge embeddings. Ideal for use cases requiring local, API-key-free knowledge management, such as autonomous systems or offline AI applications.

Canonical page: https://skillsregistry.net/skills/smcozart-o-owl  
JSON: https://api.skillsregistry.net/v1/skills/smcozart-o-owl

## Description

Cognitive memory for AI agents. MCP server with 5 memory types, composite weight scoring, and a knowledge graph. SQLite as source of truth, Obsidian as the view layer. Embeddings run locally, no API keys.

## Trust

- **Trust score (0–1):** 0.00
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

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

## Source

- **Source listing:** [GitHub](https://github.com/smcozart/O_Owl)

## 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": "smcozart-o-owl"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/smcozart-o-owl` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/smcozart-o-owl/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