convez.ai
SkillAutomaçãoAvançado
NickCrew

Claude Cortex

NickCrew/Claude-Cortex

Orquestração multi-modelo com revisão independente e gates de qualidade

Ver no GitHub
BomPluginScore · de 0 a 100

Framework de orquestração de desenvolvimento que coordena agentes de IA entre múltiplos provedores (Claude, Codex, Gemini). Implementa gates de qualidade obrigatórios — revisão de código independente, auditoria de cobertura de testes e verificação de lint — garantindo que nenhum agente revise seu próprio código. Estrutura fluxos de trabalho de desenvolvimento auditáveis com verificação em cada etapa.

Instalação

$npx convez-ai NickCrew/Claude-Cortex

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
70
Forks
16
Acompanhando
1
Saúde
71%
Último commit
há 4 meses
Versão
v4.7.0
Issues abertas
6
Contribuidores
3

Casos de uso

  • Coordenar múltiplos agentes de IA em revisão de código cruzada
  • Implementar gates de qualidade automáticos em pipelines de desenvolvimento
  • Estruturar loops de remediação com limites e escalação para humanos
  • Auditar cobertura de testes e aplicar padrões de lint automaticamente

Veredito

Solução robusta para times que querem automação de qualidade confiável com múltiplos modelos. Exige setup técnico complexo, mas oferece garantias reais contra loops infinitos e auto-avaliação tendenciosa de agentes.

README

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


Cortex is a development orchestration framework that coordinates AI agents across model providers. It enforces quality gates — independent code review, test coverage audits, and lint checks — so that no agent grades its own homework. The result is a structured, auditable development workflow where Claude, Codex, and Gemini collaborate with built-in verification at every step.

How It Works

Multi-model review with no self-review

Cortex's core principle: the agent that writes the code never reviews it. When Codex implements a feature, the review is routed to Claude first, then to a different model family, with same-model review as a last resort. Every review produces a structured artifact with severity levels and a pass/fail verdict.

Codex implements → Claude reviews → Codex remediates → Claude re-reviews
                   ↓ (unavailable)
                   Gemini reviews (fallback)
                   ↓ (unavailable)
                   Fresh-context Codex reviews (last resort)

Agent-loops: progressive quality gates

Every code change flows through three sequential loops, each with circuit breakers and escalation rules:

Code Change Loop    →  Implement → Independent review → Remediate P0/P1 → Re-review (max 3 cycles)
Test Writing Loop   →  Audit gaps → Write tests → Verify → Re-audit (max 3 cycles)
Lint Gate           →  Discover linter → Auto-fix → Check → Remediate (max 2 cycles)

P0/P1 findings must be resolved before the loop exits. P2/P3 findings are filed as issues automatically. If circuit breakers trigger, the agent stops and escalates to a human — no infinite remediation loops.

Skill recommendations

Skills are suggested automatically as you work via a two-layer pipeline: fast keyword matching on every prompt (~50ms), with optional semantic matching for deeper recommendations. The TUI runs a background watch daemon for continuous suggestions.

What's Inside

PathPurpose
agents/Agent definitions (specialized reviewers, implementers)
skills/Reusable skill modules — workflow guidance, review prompts, quality standards
rules/Behavioral guardrails and coding conventions
hooks/Automation hooks (skill suggestions, validation gates)
claude_ctx_py/Python CLI and TUI implementation

Key skills

  • agent-loops — The core workflow: structured implementation with independent review, test audit, and lint gates. Includes provider-aware review scripts with fallback chains.
  • test-review — Test quality and coverage auditing across modules.
  • doc-claim-validator — Validates documentation claims against actual code.
  • doc-maintenance — Systematic documentation audit and lifecycle management.

Install

macOS (Homebrew)

brew tap NickCrew/cortex
brew install cortex

post_install symlinks bundled agents, skills, rules, and schemas into ~/.claude/ automatically. Opt out with CORTEX_SKIP_LINK=1 brew install cortex.

Python (any platform)

# Recommended
pipx install claude-cortex

# Alternative
pip install claude-cortex

The Python package also installs cortex-minimal, a smaller command surface for agent runtime environments:

uvx --from claude-cortex cortex-minimal --help
uvx --from claude-cortex cortex-minimal git --help

It exposes only git, tmux, statusline, hooks, and completions while sharing the same tested implementations as the full cortex CLI.

If you install via Homebrew and pip, whichever binary comes first in your $PATH wins. Uninstall one to avoid ambiguity.

Development

git clone https://github.com/NickCrew/claude-cortex.git
cd claude-cortex
pip install -e ".[dev]"

Quick Start

cortex install link          # Symlink bundled assets into ~/.claude
cortex install post          # Shell completions + man pages (optional)
cortex status                # Check what's active
cortex tui                   # Launch the terminal UI

CLI Overview

cortex <command> [options]
CommandWhat it does
statusShow active agents, rules, hooks, skills
agent list|statusManage agent definitions
skills list|info|recommendDiscover and inspect skills
rules list|activateManage behavioral rules
hooks list|installInstall and validate hooks
mcp list|diagnoseMCP server discovery and diagnostics
ai recommend|watchAI-powered skill recommendations
reviewRun review workflows
tuiLaunch terminal UI
docsBrowse bundled documentation
install|uninstallManage Cortex installation

Run cortex --help or cortex <command> --help for details.

Development

just test                    # Run test suite
just lint                    # Check formatting (Black)
just type-check              # Strict mypy
just docs                    # Serve docs locally

See CONTRIBUTING.md for guidelines.

Documentation

Full documentation at cortex.atlascrew.dev.

License

MIT. See LICENSE.

Ver o original no GitHub

Bom para

Relacionados