# Linksee Memory

> Use this tool when you need to provide persistent memory for AI agents, enabling them to store and retrieve information efficiently across multiple platforms. It solves problems related to data retention and retrieval, offering features like token-efficient file reading and full-text search with heat-scoring. With inputs of text data and outputs of cached and scored information, use Linksee Memory in contexts where AI agents require reliable and efficient access to stored knowledge.

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

## Description

Provides persistent memory for AI agents using six semantic layers stored in a local SQLite database. Features token-efficient file reading that caches diffs and returns only changed content on subsequent reads. Supports full-text search with heat-scoring and works across Claude Code, Cursor, and ChatGPT Desktop.

## Trust

- **Trust score (0–1):** 0.83
- **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/linksee-memory)
- **Repository:** <https://github.com/michielinksee/linksee-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": "linksee-memory"
    }
  }
}
```

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