Multi-agent research automation framework for LLM agents, with adversarial lab meetings, paper-review rounds, auditable Markdown workflows, an autonomous runtime watchdog, and a pixel-art web dashboard.

Agent OS: keep specialist agents in a hub, spin up a temporary orchestrator per task. Local-first, works with any model.

Structured multi-perspective deliberation for hard decisions. Run full councils, focused triads, or duo debates across Claude Code, Codex, Gemini CLI, and OpenCode.