# inkwell-memory

> inkwell-memory — veronchenko-inkwell-memory. Use this tool when you need to provide AI agents with persistent memory and efficient information retrieval. It solves problems of knowledge retention and recall by leveraging Markdown files, hybrid search, and graph relations, allowing agents to access and build upon existing knowledge. Ideal for self-hosted applications, it offers a simple Docker-based interface for inputting and outputting data via git.

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

## Description

MCP server giving AI agents persistent memory: Markdown files as source of truth, hybrid BM25 + embedding search, typed graph relations. Self-hosted, single Docker image.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-21

## Source

- **Source listing:** [GitHub](https://github.com/veronchenko/inkwell-memory)

## 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": "veronchenko-inkwell-memory"
    }
  }
}
```

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