# stonemem

> stonemem — thekeystoneproject-stonemem. Use this tool when you need to leverage institutional memory for AI agents, solving problems of knowledge retention and recall across various frameworks. Stonemem provides a compiled Rust MCP server with adapters for multiple AI platforms, accepting input from these frameworks and outputting relevant knowledge and insights. It is ideal for use cases requiring persistent memory and information sharing between AI agents and frameworks like Hermes, CrewAI, and LangGraph.

Canonical page: https://skillsregistry.net/skills/thekeystoneproject-stonemem  
JSON: https://api.skillsregistry.net/v1/skills/thekeystoneproject-stonemem

## Description

Institutional memory engine for AI agents — compiled Rust MCP server with adapters for Hermes, CrewAI, LangGraph, Haystack, OpenHands, MS Agent Framework, and Google ADK

## Trust

- **Trust score (0–1):** 1.00
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/thekeystoneproject/stonemem)

## 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": "thekeystoneproject-stonemem"
    }
  }
}
```

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