# Longmem

> Use this tool when you need to leverage previously solved programming problems to aid in coding tasks, as it indexes and searches past solutions using hybrid semantic and keyword search. Longmem solves problems of knowledge retention and reuse, providing a persistent memory for AI coding assistants. It integrates with various coding tools, accepting problem descriptions as input and outputting relevant past solutions, making it ideal for use in coding and development contexts.

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

## Description

Longmem provides persistent memory capabilities for AI coding assistants by indexing and searching previously solved programming problems. It uses hybrid semantic and keyword search to find relevant past solutions, supports saving confirmed solutions with metadata, and integrates with Cursor and Claude Code. Stores data locally using SQLite with Python 3.11+.

## Trust

- **Trust score (0–1):** 0.86
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-09-28

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/gh-marerem-longmem)
- **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": "gh-marerem-longmem"
    }
  }
}
```

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