# Amber

Provides long-term memory across sessions, storing decisions and project context. Useful when you need your assistant to recall details without manual tagging.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 1
- Author: ambermem
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/ambermem/amber
- Updated: 2026-10-11
- HTML: https://affpapa.org/en/nevibecode/mcp/amber

## What it does

Amber runs as a remote service that stores atomic facts extracted during conversations. Instead of dumping raw chat logs, the assistant splits discussion points into discrete notes and generates at least five semantic variations for each. Embeddings are created via dedicated vector endpoints, keeping generative chat models away from raw memory contents.

Retrieval relies on a hybrid pipeline combining vector search with keyword matching via Reciprocal Rank Fusion. It handles informal time frames like "3 days ago" by parsing them into calendar ranges. Infrastructure runs on Cloudflare Workers edge nodes backed by isolated Turso instances for every account.

A PayPal account is mandatory because identity verification and billing depend on it. Self-hosting is not supported. Testing runs free for 90 days, after which pricing is $2.99 monthly, with full JSON export available whenever needed.

## Requirements
- Remote server: `https://mcp.ambermem.com`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http amber https://mcp.ambermem.com
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add amber --url https://mcp.ambermem.com
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "amber": {
            "url": "https://mcp.ambermem.com"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "amber": {
            "type": "http",
            "url": "https://mcp.ambermem.com"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http amber https://mcp.ambermem.com
```

## When to use it
- recall previous architectural decisions across fresh conversations
- search remembered facts using varied semantic phrasing and synonyms
- filter stored notes using natural temporal expressions
- retain personal preferences and context across multiple AI clients

## Example prompts
- What library did we decide to use for background jobs last week?
- Check our stored notes for the API endpoint conventions we agreed on.
- Export all my stored memories as a JSON file.

## 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

---
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