# Memori

> Use this tool when you need to efficiently capture and retrieve knowledge from interactions, reducing context tokens while maintaining accuracy. Memori solves problems of knowledge extraction, context maintenance, and information retrieval, providing outputs of structured facts, preferences, rules, and summaries from input interactions. It is ideal for use cases requiring intelligent memory recall and augmentation, such as conversational AI and knowledge management systems.

Canonical page: https://skillsregistry.net/skills/memori  
JSON: https://api.skillsregistry.net/v1/skills/memori

## Description

Memori provides SQL-native memory infrastructure that continuously captures interactions, extracts structured knowledge into facts, preferences, rules, and summaries, and intelligently retrieves relevant memory. The MCP server exposes recall and advanced augmentation tools that maintain context across sessions, reducing prompt tokens by over 95% compared to full-context approaches. Evaluated on the LoCoMo benchmark with 81.95% accuracy while using only 4.97% of full-context tokens.

## 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:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-28

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/memori)
- **Repository:** <https://github.com/memorilabs/memori-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": "memori"
    }
  }
}
```

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