Aigon uses four modes across two axes: number of agents and level of autonomy. All four modes apply to features. Research supports Drive and Fleet only. Feedback does not use execution modes.

                    One Agent          Multi-Agent
                 ┌──────────────┬──────────────────┐
  Hands-on       │    Drive     │      Fleet       │
                 ├──────────────┼──────────────────┤
  Hands-off      │  Autopilot   │      Swarm       │
                 └──────────────┴──────────────────┘

Drive

One agent, hands-on. You guide the implementation step by step.

• Best for: most features, learning the workflow, tight control
• Workspace: branch or worktree
• Slash command: /aigon:feature-start 07
• CLI: aigon feature-start 07

Fleet

Multiple agents, hands-on competition. Agents work in isolated worktrees on the same spec. You evaluate and pick the winner.

• Best for: important features where you want the best approach
• Workspace: one worktree per agent
• Slash command: /afs 07 cc gg cx
• CLI: aigon feature-start 07 cc gg cx

Autopilot

One agent, hands-off. The agent retries in a loop until validation passes or the iteration budget runs out. Each iteration spawns a fresh agent session.

• Best for: well-scoped features with clear validation checks
• Workspace: branch or worktree
• Slash command: /aigon:feature-do 07 --autonomous
• CLI: aigon feature-do 07 --autonomous

Swarm

Multiple agents, hands-off. Fleet + Autopilot — multiple agents compete, each running autonomously.

• Best for: maximum coverage with minimal supervision
• Workspace: one worktree per agent
• CLI: aigon feature-start 07 cc gg --autonomous --auto-submit

Mode selection guide

Command surfaces

Each mode works with both CLI and slash commands:

Agent status tracking

As agents work, they signal status transitions via aigon agent-status:

Check status:

aigon status              # All in-progress features
aigon status 31           # One feature, per-agent table