Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.crewship.ai/llms.txt

Use this file to discover all available pages before exploring further.

​
Your First Crew

A crew is a team of AI agents that work together on tasks. Each crew runs inside a shared Docker container, and agents communicate through the sidecar proxy.

​
Core Concepts

Crew

A named team with a shared container, identity, and purpose. One container per crew (not per agent).

Agent

An AI-powered worker with a persona, role, and tool profile. Runs as Exec inside the crew container.

Mission

A multi-task objective orchestrated by a Lead agent. Tasks can have dependencies and retry logic.

​
Agent Roles

Every agent has one of two roles that determines their capabilities:
RolePurposeCapabilities
AGENTIndividual contributorExecutes assigned tasks, writes code, runs tools
LEADTeam orchestratorAssigns tasks to agents, creates missions, monitors progress
Roles are functional, not hierarchical. A Lead is an equal colleague with orchestration responsibility — not a boss. This is a core Crewship philosophy (the “Crewship Adventure” ethos).

​
Creating a Crew

1

Navigate to the Crews page

Open the Crewship dashboard and click Crews in the sidebar.
2

Create a new crew

Click New Crew and fill in the details:
  • Name: A human-readable name (e.g., “Engineering”)
  • Slug: URL-friendly identifier (e.g., engineering)
  • Icon: A lucide icon name (terminal, rocket, clipboard, etc.) — not emoji
  • Color: A palette ID (blue, emerald, violet, amber, rose, cyan, lime, fuchsia) — not hex
3

Add agents to the crew

Each agent needs:
  • Name and slug: Identity (e.g., “Viktor” / viktor)
  • Role title: Human-readable role (e.g., “Backend Engineer”)
  • Agent role: AGENT or LEAD
  • CLI adapter: Which coding CLI to use (CLAUDE_CODE, CODEX_CLI, GEMINI_CLI, OPENCODE, CURSOR_CLI, FACTORY_DROID)
  • Tool profile: Controls available tools:
    • MINIMAL — Read, Search, Grep only
    • CODING — Full coding tools
    • FULL — All tools available
  • System prompt: The agent’s persona and instructions
  • Memory enabled: Toggle persistent memory across sessions
4

Assign credentials

Add API keys for the LLM provider your agents will use. Credentials are encrypted with AES-256-GCM and injected via the sidecar proxy — never as environment variables.
Settings -> Credentials -> Add Credential
Agents created from templates or through the internal API have credentials auto-assigned (autoAssignCredentials matches on provider). Agents created via the CLI or UI assign credentials manually.

​
Running Your First Mission

1

Send a message to a Lead agent

Navigate to the crew chat and send a task to the Lead:
"Analyze the current directory structure and create a summary report"
2

Lead orchestrates the work

The Lead agent can:
  • Execute the task directly
  • Assign subtasks to other agents via /assign
  • Create a multi-task mission via /mission/create
3

Monitor progress

Watch real-time progress in the chat panel. Assignments appear with status indicators:
  • PENDING — Waiting to start
  • RUNNING — Agent is working
  • COMPLETED — Task finished successfully
  • FAILED — Task encountered an error

​
Crew Container Architecture

When a crew starts, Crewship creates a shared container with this filesystem layout: 
/crew/
  agents/
    {agent-slug}/           # Each agent's home directory
      .memory/              # Persistent memory (AGENT.md, daily/*.md)
      .mcp.json             # MCP server configuration
  shared/                   # All crew members can read/write
/output/
  {agent-slug}/             # Output files visible in Files panel
/secrets/
  {agent-slug}/             # Read-only credential files
    .env                    # Maps env var names to file paths
    GH_TOKEN                # One file per credential
/workspace/                 # Temporary scratch space
Files agents create in /output/{slug}/ are immediately visible in the Files panel of the UI. Use the shared crew space at /crew/shared/ for cross-agent collaboration.

​
System Prompt Assembly Order

For the full 2-stage breakdown, see Architecture > System Prompt Assembly. When an agent starts, its system prompt is assembled in this order: 
1. Crewship system preamble (filesystem layout, credentials docs)
2. [CREWSHIP ETHOS] block (role-specific adventure context)
3. [AGENT IDENTITY] (name, role, crew)
4. User-defined system prompt (persona)
5. [SKILLS AVAILABLE] (injected skill playbooks)
6. [CREW CONTEXT] (Lead only: crew member list + API docs)
7. [PEER CONTEXT] (non-Lead agents: peer communication)
8. [CONVERSATION HISTORY] (recent messages, 60% of remaining token budget)
9. [AGENT MEMORY] (persistent memory, 40% of remaining token budget)
10. [MEMORY INSTRUCTIONS] (how to write/read memory files)
The token budget is managed with a 60/40 split: 60% for conversation history, 40% for memory context. The maximum system prompt token budget is defined in internal/tokenutil/.

​
Example: Seed Data Crew

The built-in seed data creates this Engineering crew:
AgentRoleProfileAdapter
TomasTechnical Architect (LEAD)FULLCLAUDE_CODE
ViktorBackend Engineer (AGENT)CODINGCLAUDE_CODE
NelaFrontend Engineer (AGENT)CODINGCLAUDE_CODE
MartinInfrastructure Engineer (AGENT)CODINGCLAUDE_CODE