convez.ai
MCP ServerAutomaçãoIntermediário
sageox

SageOx (ox) CLI

sageox/ox

Contexto compartilhado e memória coletiva para equipes AI-native

Ver no GitHub
BomPluginScore · de 0 a 100

Infraestrutura de contexto para engenharia agnóstica que funciona como um 'hivemind' compartilhado entre desenvolvedores e agentes de IA. Captura discussões de equipe, sessões de coding e decisões arquiteturais, tornando esse conhecimento automaticamente disponível para todos os coworkers de IA.

Instalação

$npx convez-ai sageox/ox

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
68
Forks
25
Acompanhando
2
Saúde
87%
Último commit
há 1 dia
Versão
v0.26.0
Issues abertas
195
Contribuidores
8

Casos de uso

  • Alinhar agentes de IA com padrões arquiteturais da equipe
  • Capturar e reutilizar decisões de design entre sessões
  • Manter contexto de segurança e convenções de código persistente
  • Facilitar trabalho colaborativo entre humanos e agentes

Veredito

Solução sólida e bem pensada para o desafio real de alinhar múltiplos agentes de IA com contexto corporativo. Ideal para equipes que trabalham exclusivamente com prompts e precisam de coerência entre sessões. Ainda em alfa, requer investimento em configuração inicial.

README

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

SageOx CLI (ox)

docs: ai-human-docs

SageOx is agentic context infrastructure — we call it the hivemind. It makes architectural and product intent persistent and automatically available across humans and agents.

This initial version is intended for AI-native teams — teams that build products almost exclusively through prompts.

Sessions, ledgers, and team knowledge ensure your AI coworkers understand your project's patterns, security requirements, and architectural decisions from the start, making agentic engineering multiplayer by default.

Demo

SageOx CLI Demo

Install the CLI

Quick install (macOS / Linux / FreeBSD):

curl -sSL https://raw.githubusercontent.com/sageox/ox/main/scripts/install.sh | bash

From source:

git clone https://github.com/sageox/ox.git && cd ox
make build && make install

Set up ox in your repo

# cd into your code repo (e.g. ~/src/my-project)
cd ~/src/my-project
ox login

# one time setup, done ONCE per repo
ox init
# commit the changes in your repo, e.g. git commit -a -m 'SageOx init'

ox doctor
# ox doctor --fix may be needed in the alpha stage
ox status
# will give you the location of the team context and ledger repos

👥 Go to sageox.ai - Setup team

Go into your newly created team in SageOx and invite your coworkers by copying the invite in the upper right, displayed in Team Overview.

🎙️ Record discussions

Team discussions impacting the product are captured and transcribed in the app and the context is automatically available to Claude.

🤖 Capture sessions

ox-session capture the conversation between a developer and Claude so the decisions, patterns, and reasoning become available to the rest of the team.

pwd
/home/me/src/my-project
claude
/ox-session-start
<implement fizz buzz>
/ox-session-stop

🚀 Just Ask

Start your AI coworker in your repo and just ask:

  • "What decisions were made in the last coding session on this project?"
  • "Create a plan of work based on the SageOx team discussions from today."
  • "Look at my team's SageOx coding sessions from this week and teach me a really effective prompt that was used."

⚙️ How it works

  1. ox init creates a .sageox/ directory with shared team context for your project
  2. ox integrate sets up hooks so your AI coworker automatically loads context at session start
  3. Your AI coworker receives team context, security conventions, and architectural patterns
  4. Coworkers (human and AI) share context through ledgers and team knowledge

SageOx in Practice

Here's a real example from PR #4:

flowchart LR
    subgraph discuss ["🎙️ Ryan and Ajit Discuss"]
        A1["Captured in Team Context"]
    end
    subgraph implement ["🤖 Ajit Implements"]
        B1["Captured in Ledger"]
    end
    subgraph review ["🚀 Ryan Reviews"]
        C1["Code + Session + Transcript"]
    end
    discuss --> implement --> review

Ryan and Ajit discussed the daemon design in a recorded team discussion. Ajit then implemented it with Claude (session captured in the ledger). When Ryan reviewed the PR, he had the full picture — the original discussion audio, the implementation session, and the code.

⚙️ Configuration

SageOx looks for configuration in:

  1. CLI flags (--verbose, --quiet, --json)
  2. Environment variables (OX_* prefix)
  3. Config file (.sageox/config.yaml)

Legal

Ver o original no GitHub

Bom para

Relacionados