# memory-lean

> memory-lean — zamansheikh-memory-lean. Use this tool when you need to efficiently search and retrieve specific information from a large knowledge graph without having to read the entire dataset. The memory-lean server solves the problem of slow and resource-intensive memory searches, providing a fast and token-lean alternative for AI coding agents. It accepts git-based inputs and outputs relevant information, making it ideal for use cases where quick access to specific knowledge is required.

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

## Description

A token-lean MCP memory server for AI coding agents: a knowledge graph your agent can search without reading the whole thing. Drop-in replacement for the reference memory server.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-10-16

## Source

- **Source listing:** [GitHub](https://github.com/zamansheikh/memory-lean)

## 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": "zamansheikh-memory-lean"
    }
  }
}
```

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