# cogvault

> cogvault — nbibikov-cogvault. Use this tool when you need to manage local memory for AI agents with hybrid recall capabilities, supporting multi-tenant environments without relying on cloud or Docker infrastructure. It solves problems of data storage and retrieval for AI models, providing a simple interface for inputting and outputting Markdown files. Ideal for use cases requiring secure, self-contained, and efficient memory management, with seamless integration with git for version control.

Canonical page: https://skillsregistry.net/skills/nbibikov-cogvault  
JSON: https://api.skillsregistry.net/v1/skills/nbibikov-cogvault

## Description

Fleet-grade local memory for AI agents over plain Markdown — hybrid recall, multi-tenant, one process, no cloud/Docker/LLM

## Trust

- **Trust score (0–1):** 0.48
- **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/NBibikov/cogvault)

## 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": "nbibikov-cogvault"
    }
  }
}
```

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