You write the ticket.
Your agents ship it.
Fleet is a single Go binary that orchestrates the Claude Code agents you already run — so a dev agent opens a PR, a reviewer agent picks it up, and a release agent merges it, without you in every handoff.
Define your fleet in YAML, start it in one command
An agent's role is its prompt. You declare the roles; Fleet runs them, each in its own tmux session and git worktree.
# .fleet/config.yaml
agents:
- name: backend-dev
role: developer
model: claude-sonnet
- name: code-reviewer
role: reviewer
model: claude-opus # judgment-heavy → better model
- name: release-manager
role: release-manager
model: claude-sonnetCheap models for routine roles, a stronger model where judgment matters. Then start the fleet and let the event bus move work between agents. See the full walkthrough in the step-by-step guide.
What you'd build by hand vs. what Fleet handles
You can wire this together yourself with tmux and worktrees. Here's what you'd be signing up to maintain.
The DIY approach
- Open a terminal per agent and a worktree per branch
- Notice when one agent finishes and manually tell the next to start
- Relay context between agents by reading output and re-prompting
- Cap how long each agent runs by babysitting sessions yourself
- Hope nobody's agent deletes tests to make them pass
- Reconstruct what happened from git history when something breaks
With Fleet
- Each agent gets its own tmux session and worktree automatically
- A dev agent opens a PR; a reviewer agent picks it up via the event bus
- Context moves across handoffs through structured fabric events
- Per-agent run-time budgets with hard ceilings
- A separate risk model auto-quarantines a drifting agent before it ships
- Every decision written to an audit trail you can query with fleet log
Dig deeper
Guides, comparisons, and reference for running an agent fleet.
Guides →
Step-by-step: parallel agents, PR review, cost control.
Comparisons →
Fleet vs. Devin, OpenHands, Cursor, Claude Squad, and more.
Glossary →
Plain-language definitions for the AI agent fleet era.
Agent templates →
Role-tuned starting points for every agent in your fleet.
Integrations →
Claude Code, GitHub, MCP, tmux, and the rest of your stack.
Docs →
Install, configure, and run Fleet end to end.
Need to convince your lead?
The business case — cost, governance, and audit trails — laid out for engineering leaders.
The case for FleetA note on access
Fleet is in closed beta. The binary is free to install and inspect; starting agents requires a license. Request access and we'll send a registration code.
Request access