# Leptin

> Use this tool when you need to optimize AI coding agent memory by efficiently managing tokens and reducing redundancy. Leptin solves problems of memory overload and data duplication by providing features like deduplication, merging, and decay, while also tracking token savings. It is ideal for use cases where AI agents require streamlined memory management to improve coding efficiency and accuracy.

Canonical page: https://skillsregistry.net/skills/lionellau-leptin  
JSON: https://api.skillsregistry.net/v1/skills/lionellau-leptin

## Description

Token-budgeted MCP memory for AI coding agents, with dedup, merge, decay, and a savings ledger.

## Trust

- **Trust score (0–1):** 0.66
- **Verification tier:** scanned
- **Last scanned:** 2026-08-31

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** other
- **Updated:** 2026-08-31

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/w71e6n5i5b)
- **Repository:** <https://github.com/lionellau/leptin>

## 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": "lionellau-leptin"
    }
  }
}
```

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