Autonomous orchestration framework for Claude Code with MemPalace-inspired memory (4-layer stack, 818-token wake-up), parallel-first Agent Teams (6 teammates), Aristotle First Principles methodology, and 4-stage quality gates. 925+ tests, 22 active hooks, automatic learning pipeline.
This repository also configures its own agents. See what multi-agent-ralph-loop tells them →
alfredolopez80/multi-agent-ralph-loop
Agent Claude Code
Adversarial cross-validation that a plan's implementation covers ALL details: two independent passes, the second one run in a fresh context so it cannot inherit the first's blind spots. Each pass challenges the other's assessment.
alfredolopez80/multi-agent-ralph-loop
Agent Claude Code
You are an AI Output & Code Review Super-Auditor.
alfredolopez80/multi-agent-ralph-loop
Agent Claude Code
Architectural compliance review and system design analysis. Evaluates changes against established patterns and component boundaries.
alfredolopez80/multi-agent-ralph-loop
Agent Claude Code
Autonomous researcher - iteratively modifies code, runs experiments, evaluates metrics, keeps improvements. Never stops unless budget exhausted or manually interrupted.
alfredolopez80/multi-agent-ralph-loop
Agent Claude Code
Explicit opt-in code reviewer that drives the Codex CLI. Use ONLY when the user asks for a Codex review by name — never as a default reviewer, an automatic second opinion, or a fallback. For ordinary reviews use ralph-reviewer or ralph-security.
alfredolopez80/multi-agent-ralph-loop
Agent Claude Code
Debug specialist for complex issues: reproduce, isolate, trace the cause, apply the smallest fix, verify.
alfredolopez80/multi-agent-ralph-loop
Agent Claude Code
Documentation specialist. Writes long-form docs and READMEs directly with Claude — no external CLI required.
alfredolopez80/multi-agent-ralph-loop
Agent Claude Code
Frontend/UX specialist. Claude-native reviewer: reads the code and evaluates WCAG, accessibility, performance, responsiveness, and UX directly.
alfredolopez80/multi-agent-ralph-loop
Agent Claude Code
Analyzes feature requests for missing requirements, edge cases, and ambiguities BEFORE implementation. Prevents rework by finding gaps early.
alfredolopez80/multi-agent-ralph-loop
Agent Claude Code
Rigorous Python code reviewer with strict quality standards. Emphasizes type hints, Pythonic patterns, and testability.
alfredolopez80/multi-agent-ralph-loop
Agent Claude Code
Rigorous TypeScript code reviewer with high quality standards. Emphasizes type safety, modern patterns, and testability.
alfredolopez80/multi-agent-ralph-loop
Agent Claude Code
Architecture guardian that enforces patterns, validates implementations against specs, and maintains project coherence. Spawned by orchestrator before and after each implementation step.
alfredolopez80/multi-agent-ralph-loop
Agent Claude Code
Smart Memory-Driven Orchestration with parallel memory search. Lead Software Architect coordinator with Plan-Sync validation, task classification, Aristotle First Principles methodology, living knowledge vault, and memory context from vault (Obsidian), handoffs, ledgers. Coordinates 6 ralph- teammates including…
alfredolopez80/multi-agent-ralph-loop
Agent Claude Code
Analyzes codebases to identify design patterns, anti-patterns, naming inconsistencies, and code duplication.
alfredolopez80/multi-agent-ralph-loop
Agent Claude Code
Synchronizes downstream plan steps after implementation drift. Spawned by orchestrator after each step completes to patch stale references.
alfredolopez80/multi-agent-ralph-loop
Agent Claude Code
Agente que transforma prompts ordinarios en prompts profesionales para IA usando arquitectura en 5 capas.
alfredolopez80/multi-agent-ralph-loop
Agent Claude Code
Fast, pragmatic code audit for correctness, simplicity, security, and test coverage. Part of the validation gate in step 7.
alfredolopez80/multi-agent-ralph-loop
Agent Claude Code
Specialized coding teammate for Agent Teams. Implements features, fixes bugs, and refactors code following Ralph quality gates. Use when code changes are needed: new features, bug fixes, refactoring, or performance improvements.
alfredolopez80/multi-agent-ralph-loop
Agent Claude Code
Frontend specialist teammate for Agent Teams. Loads DESIGN.md for design consistency, enforces WCAG 2.1 AA, tests 8 component states. Use when implementing frontend features, UI components, or visual elements. Context: User needs a new UI component user: "Create a pagination component for the dashboard" assistant…
alfredolopez80/multi-agent-ralph-loop
Agent Claude Code
Research and exploration teammate. Use this agent when codebase exploration, documentation lookup, or external research is needed. Context: Team needs to understand an unfamiliar library user: "How does the flock file-locking mechanism work on macOS?" assistant: "I'll spawn ralph-researcher to investigate flock…
alfredolopez80/multi-agent-ralph-loop
Agent Claude Code
Code review teammate with security and quality focus. Reviews code changes for anti-patterns, vulnerabilities, and style violations. Use when code needs review before merge, after implementation, or for quality assessment.
alfredolopez80/multi-agent-ralph-loop
Agent Claude Code
Security specialist teammate for Agent Teams. Combines threat modeling, code audit, secrets scanning, dependency CVE checks, plan security review, and hooks integrity verification. Use when: security review, vulnerability assessment, threat modeling, pre-deployment audit. Context: New auth endpoint added user: "Review…
alfredolopez80/multi-agent-ralph-loop
Agent Claude Code
Testing teammate for unit and integration tests. Use this agent when tests need to be written, run, or validated. Context: New feature implemented by ralph-coder user: "Add tests for the new worktree isolation feature" assistant: "I'll spawn ralph-tester to create unit and integration tests for worktree isolation."…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: