# Kybase

> Kybase — kyrzin-kybase. Use this tool when you need to provide AI agents with a persistent memory for storing and retrieving knowledge. Kybase solves problems related to note management, information retrieval, and knowledge exploration, enabling agents to learn and improve over time. It accepts knowledge inputs and outputs relevant information through semantic search and graph-based exploration, ideal for use cases requiring long-term memory and contextual understanding.

Canonical page: https://skillsregistry.net/skills/kyrzin-kybase  
JSON: https://api.skillsregistry.net/v1/skills/kyrzin-kybase

## Description

A self-hosted knowledge base that provides persistent memory for AI agents via MCP, enabling note management, semantic search, and graph-based knowledge exploration.

## Trust

- **Trust score (0–1):** 0.65
- **Verification tier:** scanned
- **Last scanned:** 2026-09-03

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-03

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/w5kajdtb92)
- **Repository:** <https://github.com/Kyrzin/kybase>

## 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": "kyrzin-kybase"
    }
  }
}
```

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