nyldn / claude-octopus

Claude Octopus Multi-LLM orchestration plugin for Claude Code — coordinates Codex, Gemini, Perplexity, OpenRouter, Copilot, Qwen, and Ollama with consensus gates. Eight tentacles, zero blind spots. 🐙 **Research, build, review, and ship — with eight AI providers checking each other's work.** Say what you need, and the right workflow runs. A 75% consensus gate catches disagreements before they reach production. No single model's blind spots slip through. 🧠 **Remembers across sessions.** Integrates with claude-mem for persistent memory — past decisions, research, and context survive session boundaries. ⚡ **Spec in, software out.** Dark Factory mode takes a spec and autonomously runs the full pipeline — research, define, develop, deliver. You review the output, not every step. 🔄 **Four-phase methodology, not just tools.** Every task moves through Discover → Define → Develop → Deliver, with quality gates between phases. Other orchestrators give you infrastructure. Octopus gives you the workflows. 🐙 **32 specialized personas** (role-specific AI agents like security-auditor, backend-architect), **47 commands** (slash commands you type), **50 skills** (reusable workflow modules). Say "audit my API" and the right expert activates. Don't know the command? The smart router figures it out. 🐙 **Works with just Claude. Scales to eight.** Zero providers needed to start. Add them one at a time — each activates automatically when detected. 💰 **Five providers cost nothing extra.** Codex and Gemini use OAuth (included with subscriptions). Qwen has 1,000-2,000 free requests/day. Copilot uses your GitHub subscription. Ollama runs locally for free. --- What's New | Version | Best Features | |---------|--------------| | **v9** (current) | 8 providers (Codex, Gemini, Copilot, Qwen, Ollama, Perplexity, OpenRouter, Claude). Four-way AI debates. Smart router — just say what you need. 92% faster execution. Context-aware warnings. Session handoff across conversations. Adversarial review in every workflow. | | **v8** | Multi-LLM code review with inline PR comments. Parallel workstreams in isolated git worktrees. Reaction engine — auto-responds to CI failures. 32 specialized personas. Dark Factory autonomous pipeline. | | **v7** | Double Diamond workflow. Multi-provider dispatch. Quality gates and consensus scoring. Configurable sandbox modes. | Full changelog → Star History --- Quickstart That's it. Setup detects installed providers, shows what's missing, and walks you through configuration. You need **zero** external providers to start — Claude is built in. Alternative install methods **From the Claude Code UI:** Type in a session → **Marketplace** tab → install **octo**. **Factory AI (Droid):** Update / Troubleshooting --- Top 8 Tentacles 🐙 Eight commands — one per arm. *A real octopus has eight arms, each with its own neurons that can act independently.* These eight tentacles work the same way: each orchestrates up to three AI providers, applies quality gates, and produces a deliverable. Plus 30 more: review, debug, extract, deck, docs, schedule, parallel, sentinel, brainstorm, claw, doctor, and the full set. Don't remember the command name? Just describe what you need: The smart router parses your intent and selects the right workflow. --- Which Tentacle? Not sure which command to use? Pick by goal: | I want to... | Use | |--------------|-----| | Research a topic thoroughly | or | | Debate two approaches | | | Build a feature end-to-end | | | Design a UI or style system | | | Review existing code | | | Write tests first, then code | | | Scan for vulnerabilities | | | Write a product spec | | | Go from spec to shipping code | | | Debug a tricky issue | | | Just run something quick | | Or skip the table — type or just say , and the smart router picks for you. 🔍 --- How It Works Eight Tentacles, One Workflow Claude Octopus coordinates up to eight AI providers — one per tentacle: | Provider | Role | |----------|------| | 🔴 Codex (OpenAI) | Implementation depth — code patterns, technical analysis, architecture | | 🟡 Gemini (Google) | Ecosystem breadth — alternatives, security review, research synthesis | | 🟣 Perplexity | Live web search — CVE lookups, dependency research, current docs | | 🌐 OpenRouter | Alternative model routing — access 100+ models via single API | | 🟢 Copilot (GitHub) | Zero-cost research — uses existing GitHub Copilot subscription | | 🟤 Qwen (Alibaba) | Free-tier research — 1,000-2,000 requests/day via Qwen OAuth | | ⚫ Ollama (Local) | Zero-cost local LLM — offline, privacy-sensitive, fallback | | 🔵 Claude (Anthropic) | Orchestration — quality gates, consensus building, final synthesis | Providers run in parallel for research, sequentially for problem scoping, and adversarially for review. A 75% consensus quality gate prevents questionable work from shipping. Only Claude is required — all others are optional and auto-detected. Double Diamond Phases Four structured phases adapted from the UK Design Council's methodology: | Phase | Command | What happens | |-------|---------|-------------| | Discover | | Multi-AI research and broad exploration | | Define | | Requirements clarification with consensus | | Develop | | Implementation with quality gates | | Deliver | | Adversarial review and go/no-go scoring | Run phases individually or all four with . Configure autonomy: supervised (approve each phase), semi-autonomous (intervene on failures), or autonomous (run all four). 32 Personas Specialized agents that activate automatically based on your request. When you say "audit my API for vulnerabilities," security-auditor activates. When you say "design a dashboard," ui-ux-designer takes over. Categories: Software Engineering (11), Specialized Development (6), Documentation & Communication (5), Research & Strategy (3), Business & Compliance (3), Creative & Design (4). Full persona reference | All 50 skills Reaction Engine When agents create PRs,…