# Continuo Memory

> Use this tool when you need to retain long-term context and manage large knowledge bases with efficient semantic search capabilities. Continuo Memory solves problems of information overload and context loss by providing hierarchical compression and three-tier memory storage. It takes in content and embeddings as inputs and outputs search results, memory statistics, and compressed summaries, making it ideal for applications requiring advanced context retention and knowledge management.

Canonical page: https://skillsregistry.net/skills/gtokai-continuo-memory  
JSON: https://api.skillsregistry.net/v1/skills/gtokai-continuo-memory

## Description

A persistent memory system for MCP that implements hierarchical compression and semantic search using ChromaDB and sentence transformers. Built by D.D. and Gustavo Porto, it provides three-tier memory storage (N0 chunks, N1 micro-summaries, N2 meta-summaries) with automatic compression of older content to maintain efficiency while preserving context. The server offers tools for storing content, performing semantic searches, and retrieving memory statistics, supporting both local embeddings via sentence-transformers and cloud-based OpenAI embeddings. Useful for applications requiring long-term context retention, knowledge base management, and RAG-based retrieval where traditional context windows are insufficient.

## Trust

- **Trust score (0–1):** 0.62
- **Verification tier:** scanned
- **Last scanned:** 2026-09-02

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-02

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/gtokai-continuo-memory)
- **Repository:** <https://github.com/gtokai/continuo-memory-mcp>

## 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": "gtokai-continuo-memory"
    }
  }
}
```

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