# mem9

> mem9 — luuhung93-mem9. Use this tool when you need to persist project knowledge and session metadata across multiple tools and conversations. Mem9 solves the problem of knowledge loss between coding sessions and interactions with coding agents like Codex and Claude. It takes in project data and CLI session metadata as input and provides durable storage, making it a valuable asset in collaborative coding environments.

Canonical page: https://skillsregistry.net/skills/luuhung93-mem9  
JSON: https://api.skillsregistry.net/v1/skills/luuhung93-mem9

## Description

Mem9 is an open-source, project-scoped memory service for Codex, Claude, and other MCP-compatible coding agents. It keeps durable project knowledge and CLI session metadata available across tools and conversations.

## Trust

- **Trust score (0–1):** 0.68
- **Verification tier:** scanned
- **Last scanned:** 2026-08-29

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** other
- **Updated:** 2026-08-29

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/jwd9vi9qpi)
- **Repository:** <https://github.com/luuhung93/mem9>

## 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": "luuhung93-mem9"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/luuhung93-mem9` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/luuhung93-mem9/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