Agentic Orchestration System
A config-driven framework that assembles specialized AI agents into deliberation councils and execution teams. No code. Just YAML, a brief, and a question worth debating.
$ aos run strategic-council# 13 agents. 6 profiles. One deliberation.
Two Orchestration Patterns
Every decision is either a debate or a build. AOS handles both.
Deliberation
A neutral Arbiter frames the question. Specialist agents debate from opposing perspectives. The Provocateur stress-tests consensus. Output: a structured memo with ranked recommendations and documented dissent.
Strategic Council, Security Review, Architecture Review
Execution
A CTO Orchestrator drives the product lifecycle. Agents produce artifacts in sequence — requirements, architecture, tasks, security review. Each phase feeds the next. Output: a complete execution package ready for engineering handoff.
CTO Execution Orchestration
The Agents
13 cognitive agents, each with a distinct bias, temperament, and evidence standard.
Arbiter
Synthesize competing perspectives into actionable, ranked recommendations with documented dissent
CTO Orchestrator
Deliver a complete, buildable execution package with minimal ambiguity
Multi-Platform
Run AOS anywhere you work with AI.
Pi CLI
Native terminal experience. Run deliberations and executions from your command line with full control over profiles, domains, and output.
$ pi council run strategic-councilClaude Code
Use AOS agents directly inside Claude Code sessions. Slash commands trigger deliberations with full agent orchestration.
/aos strategic-councilGemini CLI
Run AOS workflows through the Gemini CLI adapter. Same agents, same profiles, different model backend.
$ gemini-cli aos run strategic-councilReady to orchestrate?
Install the framework. Write a brief. Let 13 agents debate your hardest question.