# Fraise

An MCP server that gives your agent a memory database: it stores facts and pulls them back with FQL queries. Useful when context has to survive between sessions.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 8
- Author: FraiseHQ
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/FraiseHQ/fraise
- Updated: 2026-10-23
- HTML: https://affpapa.org/en/nevibecode/mcp/fraise

## What it does

Fraise is a memory database for AI agents. The agent talks to it in FQL, a language with two verbs — `remember` and `recall`. A fact is written once, then looked up across full text, the graph of links, and optionally vector similarity, all in a single query.

Knowledge lives in a temporal graph with three node kinds: facts, entities, topics. Edges tie a fact to what it mentions and to what it is about, so a `recall` can begin from text, from an entity, or from a topic. Recent memories rank above older ones without you asking.

The server runs from one Docker command and needs no database provisioned beside it. Persistence across restarts is not there yet — it is the next major piece of work — so long-term production use is premature. The license is MIT.

## Requirements
- Needs: Docker

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add fraise -- docker run -i --rm ghcr.io/fraisehq/fraise:0.3.4
```

### Codex

**Platform CLI**
```bash
codex mcp add fraise -- docker run -i --rm ghcr.io/fraisehq/fraise:0.3.4
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "fraise": {
            "command": "docker",
            "args": [
                "run",
                "-i",
                "--rm",
                "ghcr.io/fraisehq/fraise:0.3.4"
            ]
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "fraise": {
            "type": "stdio",
            "command": "docker",
            "args": [
                "run",
                "-i",
                "--rm",
                "ghcr.io/fraisehq/fraise:0.3.4"
            ]
        }
    }
}
```

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add fraise docker run -i --rm ghcr.io/fraisehq/fraise:0.3.4
```

## When to use it
- give an agent memory that outlives a session
- store a fact about a project in one FQL line
- pull recent facts by topic or entity in one query
- search text, graph and vectors together
- start a memory server with a single Docker command

## Example prompts
- Remember in Fraise: "acme switched to annual billing", topic billing, entity acme
- Recall everything about billing for entity acme over the last 30 days, top 5
- What does Fraise know about entity acme?

## Similar
- [REA](https://affpapa.org/en/nevibecode/mcp/rea.md) — MCP server · ★ 386989
- [GitHub](https://affpapa.org/en/nevibecode/mcp/github.md) — MCP server · ★ 33918
- [Netdata](https://affpapa.org/en/nevibecode/mcp/netdata.md) — MCP server · ★ 81115
- [browser-use](https://affpapa.org/en/nevibecode/mcp/browser-use.md) — MCP server · ★ 119160
- [Codebase Memory](https://affpapa.org/en/nevibecode/mcp/codebase-memory.md) — MCP server · ★ 47392
- [mcp-server](https://affpapa.org/en/nevibecode/mcp/mcp-server.md) — MCP server · ★ 43872

---
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