🐙 Claude Octopus

Every AI model has blind spots. Claude Octopus supports twelve external provider integrations — Codex, Antigravity CLI, Copilot, Qwen, Ollama, Perplexity, OpenRouter, OrcaRouter, OpenCode, Cursor CLI, Grok, and Kimi Code — alongside the built-in Claude Code host, with consensus gates that flag disagreements before you ship.

Claude-native first, Octopus for escalation. Use Claude-native /init, /review, and /security-review when Claude is enough. Use Octopus when you want multiple model opinions, adversarial review, or stricter multi-LLM workflows.

Claude Octopus is an independent open-source project. It is not affiliated with, endorsed by, or sponsored by Anthropic.

🐙 Research, build, review, and ship — with twelve external providers checking the host's work. Claude-native handles the ordinary path. Octopus remains dormant until you explicitly run /octo:*, then handles the escalated path. A 75% consensus gate catches disagreements before they reach production.

🧠 Remembers across sessions. Integrates with claude-mem, agentmemory, and deja-vu 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.

🔄 Choose the workflow the task needs. Use a focused method for architecture, debugging, or TDD. Use /octo:embrace for Discover → Define → Develop → Deliver, with quality gates between phases.

🐙 31 specialized personas (role-specific AI agents like security-auditor, backend-architect), 54 commands (slash commands you type), 63 skills (reusable workflow modules). Explicit workflows select the experts they need; ordinary Claude requests do not activate Octopus.

🐙 Works with just Claude. Adds up to twelve external provider integrations. Zero external providers are needed to start. Add them one at a time — each becomes available when detected and runs only inside an explicit workflow.

💰 Five providers cost nothing extra when you already have access. Codex, Antigravity CLI, Copilot, and Cursor CLI use existing subscriptions or local auth. Ollama runs locally for free. Qwen now requires API-key or Coding-Plan auth; its free OAuth tier ended on 2026-04-15.

What's New

Reviews keep their own findings and proof packets

Reviews without an artifactId now reserve separate run IDs, so starting two reviews in the same second no longer blocks seats or overwrites findings. By default, repeated and concurrent Octopus runs within a Claude Code session also keep separate proof packets, preserving each run's events and summary. If you set OCTOPUS_PROOF_RUN_ID, use a unique value per run to keep packets separate. See review evidence.

Councils recognize unique filename citations

A council seat can cite a unique filename such as pr-watchdog.yml:249 without being marked blind because it omitted .github/workflows/. Grounding and quote verification resolve unique filenames and path suffixes, excluding copies in nested checkouts. Grounding rejects ambiguous, missing and unsafe paths, and line numbers past the end of a file. Quote verification checks matching text in the resolved file and may succeed despite an out-of-range line number. It checks uniquely matching attached context before repository suffixes. See citation verification.

🆕 v11.15.4 — Honor configured timeout budgets for probe research.

Default roster: Claude Opus 5.5 leads architecture, planning, security reasoning, and final judgment; GPT-5.6 Sol is the independent implementation/review peer; Claude Sonnet 5.5 is the standard Claude seat; Fable 5.1 remains an opt-in judgment escalation. Existing model pins and provider configuration still win. See the routing strategy.

/octo:model-config                         # inspect or override the frontier roster
OCTOPUS_OPUS5_AUTO_XHIGH=1                 # opt in to automatic xhigh Opus 5 phases
OCTOPUS_OPUS_MODEL=claude-fable-5-1        # explicitly opt in to Fable 5.1
OCTOPUS_CODEX_MODEL=gpt-6-astra            # explicitly opt in to Astra
/octo:model-config tier premium claude claude-fable-5-1  # one bounded Fable judgment seat
/octo:model-config tier premium codex gpt-6-astra        # one bounded Astra judgment seat

🆕 v9.41 — Multi-LLM Council. /octo:council runs a structured 3/5/7-persona deliberation across Claude, Codex, Antigravity, and OpenCode with goal modes (advice, decision, plan, implement, review), styles (balanced, adversarial, red-team, executive, implementation), benchmark-aware role routing, quorum + critical-veto gates, budget caps, and gated worktree handoff for approved plans. Use it when one model's opinion isn't enough.

/octo:council --goal decision --style adversarial "Should this service stay monolithic?"
/octo:council --goal implement --implement plan-only "Refactor the auth flow"

Full changelog →

V10 migration guide →

V10 adds a durable execution contract, fail-closed contribution validation, Doctor 2.0, Provider Registry 2.0, process-tree cancellation evidence, and opt-in eval routing. Existing provider and model pins still win. Automation that uses doctor --json must handle exit 1 while retaining its valid JSON body; invalid arguments return 2. See the migration guide for compatibility and rollback details.

• Current fresh configurations use GPT-5.6 Sol for Codex implementation/review, Claude Opus 5.5 for premium Claude work, and Claude Sonnet 5.5 for the standard Claude seat. Existing environment, session, and providers.json pins remain unchanged; OCTOPUS_LEGACY_ROLES=1 restores the pre-frontier role mapping.

• New claude-sdk seat env vars (v9.50): CLAUDE_SDK_API_KEY, OCTOPUS_CLAUDE_SDK_MODEL, OCTOPUS_CLAUDE_SDK_MAX_TOKENS, OCTOPUS_CLAUDE_SDK_ALLOWED_MODELS, OCTOPUS_CLAUDE_SDK_CONTEXT_BUDGET.
• Fable guards apply to `claude-fab