Back to directory

Gas Town

A workspace manager that coordinates multiple AI coding agents, such as Claude Code and GitHub Copilot, working on different tasks at once, persisting their work state in git so context survives restarts.

Gas Town

Gas Town is a multi-agent orchestration system for AI coding agents such as Claude Code, GitHub Copilot and Codex, aimed at coordinating several agents working on different tasks without losing context when an agent restarts. Work state persists in git-backed storage instead of an agent's own memory, and built-in mailboxes, identities and handoffs replace manual coordination, letting a workspace scale from a handful of agents to twenty or thirty.

A workspace, called a Town, contains project containers called Rigs, each wrapping a git repository. Worker agents, called Polecats, have a persistent identity but run in ephemeral sessions spawned per task, with their work stored in git worktree-based Hooks that survive crashes and restarts. Work items are tracked as Beads in a git-backed issue-tracking ledger, and Convoys bundle multiple beads into units assigned to agents, with automatic stall detection for large-scale work.

A primary coordinator, called the Mayor, is a Claude Code instance with full context of the workspace that a user talks to directly. It is written in Go.

More in Coding agents

See all 793
  • The City

    github.com

    A native macOS app that shows Claude Code runs as a city, with each project as a building, each team as a floor of robots, and every animation driven by a real event from the claude CLI's stream.

  • rig

    tryrig.ai

    A small, single-binary agent runtime that points at any OpenAI-compatible model, local or hosted, reads and edits a repository's code, runs its tests and remembers what it learned, with a loop implemented in a few hundred lines.

  • Jauvex

    jauvex.reindent.com

    An Electron desktop app that puts Claude Code, Codex and Grok coding-agent sessions side by side and lets you steer them by voice, with a small model handling fast routing decisions.