convez.ai
MCP ServerAutomaçãoIntermediário
fandych

Suora

fandych/suora

Desktop AI workbench local-first com chat, docs, agentes e automação

Ver no GitHub
InicialPluginScore · de 0 a 100

Workbench de IA local-first em Electron que integra chat, documentos, agentes, skills, pipelines, timers, canais e servidores MCP em uma única aplicação desktop. Combina conversa, automação e integrações sem depender de nuvem, com suporte a múltiplos provedores de modelos e conhecimento local.

Instalação

$npx convez-ai fandych/suora

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
3
Forks
0
Acompanhando
0
Saúde
28%
Último commit
há 1 mês
Versão
v0.2.4
Issues abertas
0
Contribuidores
2

Casos de uso

  • Criar workflows de automação local com agentes e pipelines
  • Gerenciar conhecimento pessoal com documentos e grafo de backlinks
  • Integrar múltiplos provedores de IA em um único ambiente
  • Agendar e executar tarefas automáticas via timers e channels

Veredito

Suora é uma solução robusta para quem busca um ambiente de IA verdadeiramente descentralizado com capacidades de automação real. Técnico e bem-estruturado, mas exige conforto com setup inicial de modelos e serverless.

README

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

What Suora Is

Suora is an Electron-based AI workbench for local knowledge work, automation, and integrations.

Current Product Surface

ModuleCurrent role
ChatConversations, attachments, tool calls, and pipeline commands
DocumentsLocal notes, folders, backlinks, source-aware graph insights, and chat context
ModelsProvider setup, model enablement, testing, and compare
AgentsBuilt-in and custom agents with testing and versioning
SkillsInstalled skills, registry browsing, SKILL.md editing, and import/export
PipelineMulti-step agent workflows with history and Mermaid preview
TimerOnce / interval / cron schedules
ChannelsExternal messaging integrations and reply routing
MCPMCP server configuration
SettingsPreferences, security, data, logs, and system diagnostics

Why It Feels Different

  • local-first desktop workspace instead of a browser-only shell
  • chat, documents, automation, and integrations in one app
  • multi-provider model strategy with BYOK and local-model support
  • built-in agents, skills, pipelines, timers, channels, and MCP as real product modules

Get Started

Download

Get the latest build from:

Run from source

npm install
npm run dev

First useful setup order

  1. Configure at least one model in Models
  2. Start a conversation in Chat
  3. Create a local knowledge area in Documents
  4. Add automation in Pipeline and Timer
  5. Connect external channels only when needed

Documentation Map

The repo now keeps a smaller maintained documentation set:

DocPurpose
FEATURES.mdShort capability index
docs/user/USER_GUIDE_ZH.mdPrimary Chinese user guide
docs/user/USER_GUIDE_EN.mdPrimary English user guide
docs/technical/TECHNICAL_DOC_ZH.mdPrimary Chinese technical reference
docs/technical/TECHNICAL_DOC_EN.mdPrimary English technical reference
docs/LLM_WIKI_CAPABILITIES.mdLLM Wiki-inspired document intelligence capability reference
docs/TESTING.mdTesting and validation notes
docs/CHANNEL_INTEGRATION.mdChannel setup and runtime notes
docs/requirements.mdScope and requirements baseline

GitHub Pages is built from website/ with Docusaurus and publishes website/build.

Development

Common commands

npm install
npm run dev
npm run build
npm run preview
npm run package
npm run lint
npm run type-check
npm run test:run
npm run test:e2e

Security Notes

  • API keys prefer OS-backed secure storage
  • if secure storage is unavailable, keys remain in memory only
  • filesystem access can be sandboxed
  • tool execution can require confirmation

License

MIT

Ver o original no GitHub

Bom para

Relacionados