Key takeaways
- From Steve Yegge, former Google/Amazon engineer — orchestrates 20-30 Claude Code instances simultaneously
- Built on Beads (225K lines of Go) — uses tmux as primary UI with seven specialized worker roles
- Designed for expert users (Stage 7-8 on Yegge's AI coding evolution scale) — 'vibe coding' at scale
FAQ
What is Gastown?
Gastown is a multi-agent orchestrator that lets developers run 20-30 Claude Code instances in parallel using tmux and git-backed data storage.
Who created Gastown?
Steve Yegge, former senior engineer at Google and Amazon, created Gastown as his fourth attempt at an agent orchestrator in 2025.
What is the relationship between Gastown and Beads?
Gastown is built on top of Beads, Yegge's 225K-line Go library for git-backed data storage that serves as the control and data plane.
Is Gastown production ready?
No, Gastown is explicitly experimental. Yegge warns the codebase is under 3 weeks old and '100% vibe coded.'
Executive Summary
Gastown is Steve Yegge's experimental multi-agent orchestrator for running 20-30 Claude Code instances in parallel.[1] Built on his Beads data system, it uses tmux as its primary UI and implements seven specialized worker roles (Mayor, Polecats, Refinery, Witness, Deacon, Dogs, and the human Overseer). Gastown is explicitly for expert users comfortable with "vibe coding" at industrial scale.
| Attribute | Value |
|---|---|
| Creator | Steve Yegge |
| Type | Open Source (Personal Project) |
| GitHub Stars | 9.3K |
| Language | Go |
| Headquarters | N/A (Independent) |
Product Overview
Gastown is an opinionated multi-agent orchestrator that Yegge describes as "Kubernetes for agents."[1] It's his fourth complete orchestrator of 2025, representing lessons learned from three failed predecessors. The system manages parallel Claude Code instances through a tmux-based interface with specialized worker roles.
The tool solves a specific problem: when running many AI coding agents simultaneously, work gets lost, agents conflict over git operations, and coordination becomes chaotic. Gastown provides structure through its "Town" and "Rig" abstractions.
Key Capabilities
| Capability | Description |
|---|---|
| Multi-Agent Parallel Execution | Run 20-30 Claude Code instances simultaneously |
| Seven Worker Roles | Mayor, Polecats, Refinery, Witness, Deacon, Dogs, Overseer |
| Merge Queue | Intelligent conflict resolution via the Refinery role |
| Git-Backed State | All state stored in git via Beads library |
| Tmux UI | Terminal multiplexer as primary interface |
Worker Roles
| Role | Description |
|---|---|
| Mayor | Main agent, concierge and chief-of-staff |
| Polecats | Ephemeral workers that swarm on tasks, produce Merge Requests |
| Refinery | Handles Merge Queue, intelligently combines changes |
| Witness | Watches polecats, helps them get unstuck |
| Deacon | Daemon beacon for system coordination |
| Dogs | Town-level monitoring and alerting |
| Overseer | You, the human operator |
Technical Architecture
Gastown is built on two key components:[2]
- Beads — A 225K-line Go library providing git-backed data storage[3]
- Tmux — Terminal multiplexer serving as the primary UI
Core Concepts
| Concept | Description |
|---|---|
| Town | Your HQ directory (e.g., ~/gt) managing all rigs |
| Rig | A single project/repo under Gastown management |
| MR (Merge Request) | Work unit produced by polecats |
| MQ (Merge Queue) | Ordered queue of MRs awaiting integration |
Key Technical Details
| Aspect | Detail |
|---|---|
| Deployment | Local (CLI + tmux) |
| Model(s) | Claude Code (and compatible CLIs) |
| Dependencies | Beads, tmux, Go runtime |
| Open Source | Yes (GitHub) |
Degradation model: Gastown degrades gracefully — every worker can operate independently, and you can run partial configurations or even "no-tmux" mode.
Strengths
- Scale — Enables 20-30 parallel agent instances, far beyond manual management
- Intelligent merging — Refinery role handles the complex "monkey knife fight" of parallel git operations
- Graceful degradation — Works in partial configurations, doesn't require full orchestration
- Expert pedigree — Built by Steve Yegge with decades of Google/Amazon engineering experience
- Open exploration — Tackles the MAKER benchmark problem (20-disc Hanoi towers) that defeats other approaches[4]
- Built on proven foundation — Beads already has tens of thousands of users
Cautions
- Explicitly experimental — Codebase under 3 weeks old at launch, "100% vibe coded"
- Expert-only — Requires Stage 7-8 on Yegge's AI coding evolution scale
- High cost — Multiple Claude Code accounts needed; "cash guzzler"
- Tmux required — Must learn tmux to use effectively
- Beads lock-in — No alternative backend; must adopt Yegge's full stack
- Chaotic by design — "Work can be chaotic and sloppy" — bugs get fixed multiple times, designs go missing
Pricing & Licensing
| Tier | Price | Includes |
|---|---|---|
| Gastown | Free | Open source |
| Claude Code | $20-100/mo | Required for each account |
True cost: Yegge mentions needing multiple Claude Code accounts and expecting to need a third within a week of launch. Heavy users should budget $100-300+/month.
Licensing model: Open source (personal project)
Competitive Positioning
Direct Competitors
| Competitor | Differentiation |
|---|---|
| Ralph | Ralph is simpler (bash loop); Gastown is full orchestration system |
| Tembo | Tembo is commercial with enterprise features; Gastown is experimental/personal |
| Manual tmux | Gastown adds structure, roles, and merge queue to raw tmux management |
When to Choose Gastown Over Alternatives
- Choose Gastown when: You're already at Stage 7-8 of AI coding evolution, comfortable with chaos, and want to push the boundaries of parallel agent execution
- Choose Ralph when: You want the simplest possible approach (bash loop) without the orchestration complexity
- Choose Tembo when: You need enterprise features, team support, and stability
Ideal Customer Profile
Best fit:
- Expert developers already managing 3-5+ parallel Claude Code instances
- Engineers comfortable with tmux and terminal-first workflows
- Researchers exploring multi-agent coordination
- Developers willing to accept chaos and instability for throughput
Poor fit:
- Anyone not already at Stage 6+ of AI coding adoption
- Teams needing stability and reliability
- Developers uncomfortable with vibe coding philosophy
- Organizations requiring enterprise support or compliance
Viability Assessment
| Factor | Assessment |
|---|---|
| Financial Health | N/A — Personal open source project |
| Market Position | Pioneer — Pushing boundaries of multi-agent orchestration |
| Innovation Pace | Rapid — Fourth orchestrator in one year |
| Community/Ecosystem | Growing — 9.3K stars, builds on Beads (tens of thousands of users) |
| Long-term Outlook | Uncertain — Depends on Yegge's continued interest |
Gastown represents cutting-edge experimentation in multi-agent orchestration. It's not production-ready and explicitly warns users away, but for the right expert users, it demonstrates what's possible.
Bottom Line
Gastown is the most ambitious open-source multi-agent orchestrator available, enabling 20-30 parallel Claude Code instances with sophisticated role-based coordination. It's explicitly experimental and only appropriate for expert users already pushing the limits of AI-assisted coding.
Recommended for: Expert developers (Stage 7-8) who want to explore the frontier of multi-agent orchestration and are comfortable with instability.
Not recommended for: Anyone seeking production stability, enterprise features, or a gentle learning curve.
Outlook: Gastown represents where multi-agent orchestration is heading. The concepts (specialized roles, merge queues, graceful degradation) will likely influence commercial tools, even if Gastown itself remains experimental.
Research by Ry Walker Research • methodology