convez.ai
MCP ServerIntegração & APIsIntermediário
ambermem

Amber - Memória Persistente para Assistentes de IA

ambermem/amber

Memória inteligente e searchable que acompanha seu assistente de IA

Ver no GitHub
InicialPluginScore · de 0 a 100

MCP server que fornece memória de longo prazo persistente e pesquisável para assistentes de IA, funcionando automaticamente durante conversas normais. Usa busca híbrida (vetor + palavra-chave), expansão de consultas e categorização automática de tópicos para recuperar informações relevantes sem configuração manual.

Instalação

$npx convez-ai ambermem/amber

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
1
Forks
0
Acompanhando
0
Saúde
37%
Último commit
há 4 dias
Versão
v1.1.0
Issues abertas
1
Contribuidores
1

Casos de uso

  • Manter contexto de projetos e decisões entre conversas
  • Armazenar preferências pessoais e detalhes de trabalho
  • Recuperar automaticamente informações relevantes sem busca manual
  • Melhorar a qualidade de respostas do assistente com histórico persistente

Veredito

Amber é uma solução sólida de memória persistente com arquitetura bem pensada (chunking semântico, busca híbrida com RRF, query expansion). Compatível com múltiplos clientes MCP (Claude, ChatGPT, Cursor, etc.), oferece boa relação custo-benefício ($2.99/mês) e transparência em privacidade. Ideal para quem quer que seu assistente de IA retenha contexto de longo prazo sem overhead manual.

README

A tradução para o português deste README ainda está na fila.

Amber

Long-term memory for AI assistants.

Amber is an MCP server that gives any AI assistant persistent, searchable memory across conversations. Your AI remembers preferences, decisions, project context, and personal details - without you doing anything special.

Just talk normally. Amber stores what matters and finds it when relevant.

Quick Install

One command. Works with any MCP-compatible client.

Claude Code / Claude Desktop

claude mcp add --transport http --scope user amber https://mcp.ambermem.com

Cursor

Add to ~/.cursor/mcp.json (or %USERPROFILE%\.cursor\mcp.json on Windows):

{
  "mcpServers": {
    "amber": {
      "url": "https://mcp.ambermem.com"
    }
  }
}

ChatGPT

Settings → Connectors → Create → URL: https://mcp.ambermem.com

Windsurf

Add to ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "amber": {
      "serverUrl": "https://mcp.ambermem.com"
    }
  }
}

VS Code (GitHub Copilot)

Add to .vscode/mcp.json:

{
  "servers": {
    "amber": {
      "type": "http",
      "url": "https://mcp.ambermem.com"
    }
  }
}

Any MCP client

URL: https://mcp.ambermem.com | Transport: Streamable HTTP | Auth: OAuth 2.1 (auto-discovered)

How It Works

  1. You talk to your AI normally. Amber stores important facts in the background.
  2. Next conversation, your AI searches Amber automatically when context would help.
  3. Memory improves over time. The more you use it, the better it gets.

No configuration. No tagging. No manual organization.

What Makes Amber Different

FeatureBasic memory serversAmber
StorageOne embedding per memoryMultiple semantic variants per fact
SearchSingle vector lookupHybrid: vector + keyword + RRF fusion
QueriesExact match onlyAuto-expanded (synonyms, paraphrases)
InputStored as-isLLM-chunked into atomic facts
TopicsManual tags or noneAuto-categorized by LLM
TimeNo temporal awarenessNatural language time parsing ("last week", "3 days ago")

Technical Details

  • 18 MCP tools (9 memory, 7 account, 2 feedback)
  • Hybrid retrieval pipeline: vector search + full-text search + Reciprocal Rank Fusion
  • LLM-powered chunking: text → atomic facts, each independently searchable
  • Multi-variant embeddings: each fact stored with ~4 paraphrases for higher recall
  • Query expansion: searches are auto-rephrased to find semantically related memories
  • Automatic topic categorization: memories grouped by LLM-generated topics
  • Temporal parsing: "what did I say last week?" just works
  • Async processing: storage completes in 10-30s background, never blocks your conversation

Pricing

  • 60-day free trial - no charge, cancel anytime
  • $2.99/month after trial, via PayPal
  • Cancel instantly - ask your AI to cancel, or cancel through PayPal directly
  • No lock-in - export all your data as JSON anytime

Privacy

  • No email collected
  • No marketing, no spam
  • Data isolated per user (separate database)
  • PayPal handles all payment info
  • Full export + account deletion available
  • GDPR compliant (data minimization by design)

Architecture

Amber runs on Cloudflare Workers (zero cold starts, global edge deployment) with Turso databases (one per user, full isolation). LLM processing uses Gemini Flash for chunking/expansion and OpenAI for embeddings.

For full technical documentation: ambermem.com/llms.txt

Links

FAQ

Will it slow my AI down? No. Storage is async (background). Search adds <1 second.

What if Amber shuts down? Export all your data as JSON anytime. Your data is always yours.

Do I need a PayPal account? Currently yes. PayPal handles both identity and billing. More login options coming soon.

Is my data safe? Each user gets a completely isolated database. No data is shared between users. Amber has no access to your PayPal payment details.

Can I self-host? Not currently. Amber is a managed service. We handle the infrastructure, scaling, and LLM costs so you don't have to.

Ver o original no GitHub

Bom para

Relacionados