archon

Orchestrate multi-session AI campaigns with persistent state and phase-based delegation.

820|78|Updated Mar 20, 2026

Search Tags:#planning #agents #orchestration #multi-session #archon #campaign

Ready to run

npx skills add https://github.com/SethGammon/Citadel --skill archon-sethgammon

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: archon
Source: https://github.com/SethGammon/Citadel/tree/main/skills/archon
Command: npx skills add https://github.com/SethGammon/Citadel --skill archon-sethgammon

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Archon addresses the difficulty of coordinating long-running, multi-session AI work by preserving context, tracking decisions, and decomposing tasks into reusable phases across agents.

Core Features & Use Cases

Persistent campaign state across sessions with memory of decisions
Phase-based decomposition with delegated work to sub-agents
Structured health checks, logging, and continuation to ensure progress over time

Quick Start

Start a new Archon campaign with a clear objective, then let Archon decompose it into phases and manage persistence across sessions.

Frequently Asked Questions about archon

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I maintain AI agent context across multiple sessions for a long-running project?▼

Multi-session AI campaigns maintain context by preserving state, tracking decisions, and injecting full context into sub-agents. This allows tasks spanning multiple sessions to resume with memory of previous progress and governance.

What is phase-based decomposition in multi-agent orchestration?▼

Phase-based decomposition breaks complex campaigns into structured phases with delegated work for sub-agents. Each phase has end conditions for deterministic execution, ensuring coordinated progress across agents over time.

How do I start a multi-session AI campaign with persistent state?▼

Start a multi-session campaign by defining a clear objective. The orchestrator decomposes the objective into phases, manages state persistence, and handles delegation to sub-agents across subsequent sessions.

Can I coordinate multiple sub-agents on a single task without losing track of decisions?▼

Yes, multi-agent orchestration tracks decisions through persistent campaign state and structured logging. This governance ensures that coordinated sub-agents retain memory of past actions and maintain progress across sessions.

When do I need multi-session orchestration for AI agents instead of a single prompt?▼

Multi-session orchestration is needed when tasks span multiple sessions requiring memory, governance, and phase-based delegation. Single prompts lack the persistent state and structured health checks necessary for long-running, coordinated campaigns.

Does multi-agent orchestration support deterministic execution for complex workflows?▼

Deterministic execution is supported through phase end conditions, campaign logging, and full-context injection to sub-agents. These features ensure that orchestrated multi-session campaigns progress predictably and maintain structured health checks.