# io.github.marerem/longmem

> Use this tool when you need to retain context and information across projects and sessions, leveraging local semantic search to retrieve relevant data. It solves problems of knowledge fragmentation and information loss, providing a unified memory for Cursor and Claude Code. The tool accepts user input and project data, outputting relevant information and insights to inform coding decisions.

Canonical page: https://skillsregistry.net/skills/io-github-marerem-longmem  
JSON: https://api.skillsregistry.net/v1/skills/io-github-marerem-longmem

## Description

Persistent cross-project memory for Cursor and Claude Code using local semantic search.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** unverified

## Facts

- **Version:** 0.2.1
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** search
- **Updated:** 2026-04-19

## Source

- **Source listing:** [MCP Registry](https://registry.modelcontextprotocol.io/v0/servers/io.github.marerem%2Flongmem)
- **Repository:** <https://github.com/marerem/longmem>

## 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": "io-github-marerem-longmem"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/io-github-marerem-longmem` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/io-github-marerem-longmem/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