# thrift-memory

> Use this tool when you need to optimize memory management in AI agent teams, reducing costs and improving efficiency. It provides cheap memory storage, token-budgeted recall, and savings tracking through a local dashboard, solving problems of costly memory usage and limited recall capabilities. Ideal for use cases where memory optimization is crucial, such as large-scale AI deployments or resource-constrained environments.

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

## Description

Provides MCP tools for cost-optimized memory management in AI agent teams, enabling cheap memory storage, token-budgeted recall with savings receipts, and a local dashboard for monitoring savings.

## Trust

- **Trust score (0–1):** 0.60
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-08-30

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/fykiqwyvj1)
- **Repository:** <https://github.com/YohadH/thrift-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": "yohadh-thrift-memory"
    }
  }
}
```

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