# Thrift

> Use this tool when you need to optimize memory storage and recall for MCP-capable agents, solving problems of costly memory usage and inefficient recall processes. It takes in memories and a token budget as inputs, and outputs relevant memory slices along with logged receipts. Ideal for use cases where memory efficiency and cost-effectiveness are crucial, such as in resource-constrained environments or large-scale agent deployments.

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

## Description

Cost-first memory layer for MCP-capable agents that stores memories cheaply and recalls relevant slices under a hard token budget, logging receipts for every recall.

## 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:** monitoring
- **Updated:** 2026-08-30

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/a6erwq9xvn)
- **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-thirft"
    }
  }
}
```

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