# squish-memory

> squish-memory — michielhdoteth-squish-memory. Use this tool when you need to streamline AI agent workflows and manage memory efficiently. It solves problems of disconnected workflows and limited memory by connecting Claude Code, Codex, ChatGPT, MCP, and local agents through a single command. The squish-memory tool takes in AI workflows and outputs a unified, local-first memory runtime, ideal for use cases requiring seamless integration and optimized memory management.

Canonical page: https://skillsregistry.net/skills/michielhdoteth-squish-memory  
JSON: https://api.skillsregistry.net/v1/skills/michielhdoteth-squish-memory

## Description

Squish gives AI agents calibrated recall confidence (ECE 0.055) and honest abstention — the only memory runtime that tells your agent how much to trust each recollection, and says I don't know when nothing clears the bar. Local-first, MIT, npm install in 30s.

## Trust

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

## 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/michielhdoteth/squish-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": "michielhdoteth-squish-memory"
    }
  }
}
```

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