# Memento

Maintains local persistent memory across chat sessions using graph and hybrid search. Useful when an assistant needs to retain architecture decisions indefinitely.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 9
- Author: scrypster
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/scrypster/memento
- Updated: 2026-02-20
- HTML: https://affpapa.org/en/nevibecode/mcp/scrypster-memento

## What it does

The server preserves context across agent sessions without routing conversational records through external clouds. It transforms project conventions, chosen tools, and developer choices into a local knowledge graph. Retrieval relies on hybrid mechanics that merge full-text indexing, vector similarity, and reciprocal rank fusion.

Built-in tools include `traverse_memory_graph` for exploring connections via multi-hop BFS and `detect_contradictions` for discovering outdated or clashing entries. Setting up requires either Docker or local Go 1.23+, Node.js 18+, and Ollama. Initial provisioning pulls around 5 GB of Ollama models, so low disk space will halt the setup.

Engineers can inspect connections through a local dashboard at `http://localhost:6363/integrations`. Pointing multiple clients at a shared PostgreSQL instance enables collaborative recall, tagging items with authors derived from git configuration.

## Requirements
- Needs: Docker

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add scrypster-memento -- docker run -i --rm ghcr.io/scrypster/memento:0.1.0
```

### Codex

**Platform CLI**
```bash
codex mcp add scrypster-memento -- docker run -i --rm ghcr.io/scrypster/memento:0.1.0
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "scrypster-memento": {
            "command": "docker",
            "args": [
                "run",
                "-i",
                "--rm",
                "ghcr.io/scrypster/memento:0.1.0"
            ]
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "scrypster-memento": {
            "type": "stdio",
            "command": "docker",
            "args": [
                "run",
                "-i",
                "--rm",
                "ghcr.io/scrypster/memento:0.1.0"
            ]
        }
    }
}
```

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add scrypster-memento docker run -i --rm ghcr.io/scrypster/memento:0.1.0
```

## When to use it
- retain architecture decisions across separate agent restarts
- run hybrid queries with full-text and vector ranking
- flag conflicting decisions and outdated records
- share engineering context across a team via PostgreSQL

## Example prompts
- Remember that we chose PostgreSQL specifically for pgvector capabilities
- Which database did we select for this repository and why?
- Recall who made the latest decision regarding the auth service

## Similar
- [REA](https://affpapa.org/en/nevibecode/mcp/rea.md) — MCP server · ★ 392262
- [GitHub](https://affpapa.org/en/nevibecode/mcp/github.md) — MCP server · ★ 33989
- [Netdata](https://affpapa.org/en/nevibecode/mcp/netdata.md) — MCP server · ★ 81163
- [browser-use](https://affpapa.org/en/nevibecode/mcp/browser-use.md) — MCP server · ★ 119231
- [Codebase Memory](https://affpapa.org/en/nevibecode/mcp/codebase-memory.md) — MCP server · ★ 47577
- [mcp-server](https://affpapa.org/en/nevibecode/mcp/mcp-server.md) — MCP server · ★ 43902

## Other versions with the same name
- [memento · veerps57](https://affpapa.org/en/nevibecode/mcp/memento.md) — ★ 24

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md