# sepia

> sepia — michael-obele-sepia. Use this tool when you need to enhance your AI coding agent's memory capabilities with a self-hosted remote knowledge-graph server. Sepia solves the problem of limited local memory by providing a scalable and reliable solution, accepting git inputs and outputting enhanced knowledge graphs. Ideal for use cases requiring large-scale knowledge management and collaboration, sepia offers a seamless upgrade from local-file memory servers.

Canonical page: https://skillsregistry.net/skills/michael-obele-sepia  
JSON: https://api.skillsregistry.net/v1/skills/michael-obele-sepia

## Description

A personal, self-hosted remote knowledge-graph memory server for AI coding agents — a drop-in upgrade from the official local-file memory MCP server

## Trust

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

## 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/Michael-Obele/sepia)

## 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": "michael-obele-sepia"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/michael-obele-sepia` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/michael-obele-sepia/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