convez.ai
MCP ServerIntegração & APIsAvançado
engram-app

Engram

engram-app/Engram

Suas notas como memória de IA, sincronizadas e consultáveis via MCP

Ver no GitHub
InicialPluginScore · de 0 a 100

Sistema RAG de conhecimento pessoal que indexa vaults do Obsidian e oferece busca vetorial via MCP server. Sincroniza bidireccionalmente suas notas markdown com assistentes de IA, transformando-as em memória persistente e consultável. Construído em Elixir/Phoenix com suporte a auto-hospedagem via Docker.

Instalação

$npx convez-ai engram-app/Engram

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
2
Forks
1
Acompanhando
0
Saúde
75%
Último commit
há 1 dia
Versão
release-v0.89.0
Issues abertas
336
Contribuidores
3

Casos de uso

  • Integrar Obsidian com Claude e outros assistentes de IA
  • Criar camada de memória persistente para agentes de IA
  • Buscar semanticamente dentro de bases de conhecimento pessoais
  • Sincronizar bidireccionalmente notas entre múltiplas interfaces

Veredito

Engram é uma solução madura e bem-documentada para quem quer conectar Obsidian com IA via MCP, oferecendo busca vetorial e sincronização bidirecional. Requer familiaridade com Docker e auto-hospedagem, mas o setup é direto e a documentação é excepcional.

README

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

Engram

Engram — your notes are your AI's memory, synced everywhere and read by your AI

Verify Last commit Stars License Sponsor Ko-fi

Your notes are your AI's memory.

The AI memory layer where your notes are the storage — markdown you and your AI assistants both read and write to via MCP. Built with Elixir/Phoenix. Pairs with the Engram Obsidian Sync plugin for real-time bidirectional sync.

Self-Host (Docker Compose)

Don't want to run the commands yourself? Open the Quickstart docs, select the whole page, and paste it into your AI assistant — it's written top-to-bottom as imperatives the AI can execute in order.

Otherwise:

git clone https://github.com/engram-app/Engram.git
cd Engram
cp .env.example .env       # then fill in the three secrets at the top
docker compose up -d

App at http://localhost:4000. Migrations run on boot. Only port 4000 is host-exposed; everything else stays on the private Docker network.

Large vaults? Enable MinIO for S3-style attachments: docker compose --profile s3 up -d — see storage docs.

Better embeddings? Switch to Voyage AI in .env — see embeddings docs.

Full self-host documentation

TopicLink
Quickstarthttps://engram.page/docs/self-host/quickstart/
Environment varshttps://engram.page/docs/self-host/environment-variables/
Encryption & keyshttps://engram.page/docs/self-host/encryption/
Backup & restorehttps://engram.page/docs/self-host/backup-restore/
Upgradeshttps://engram.page/docs/self-host/upgrade/
Troubleshootinghttps://engram.page/docs/self-host/troubleshooting/
Architecturehttps://engram.page/docs/self-host/architecture/
MCP setuphttps://engram.page/docs/mcp/
HTTP APIhttps://engram.page/docs/api/

Contributing

Local dev setup, tests, and PR rules: see CONTRIBUTING.md.

License

Dual-licensed:

External contributions sign the Engram CLA. See CONTRIBUTING.md.

Security

See SECURITY.md for vulnerability disclosure. Self-host LAN deployments are out of scope of our published SLA — security depends on the operator's network and infra.

Copyright (c) 2026 Rasbandit Software Solutions LLC d/b/a Engram.

Ver o original no GitHub

Bom para

Relacionados