Overview

Understanding Taxiway

Taxiway creates isolated labs for running and comparing AI agent orchestrators on Lima or Docker, each with a LiteLLM gateway, Caddy proxy, and optional Langfuse observability. This documentation covers how to install, use, understand, and contribute to the tool.

Reference

PagePurpose
ConceptsCore product model
CLI UsageCLI command reference
ConfigurationRuntime paths, drivers, and observability
ArchitectureSystem design

Drivers

Drivers create and operate labs.

DriverBest fitRequirementDetails
limaLocal labs on macOS and Linuxlimactl on PATHLima
dockerContainer-backed labs, Linux development, Docker-backed end-to-end coveragedocker on PATH and daemonDocker

Taxiway auto-selects Lima when limactl is available, then Docker when Docker is available.

Use --driver <name> to force a driver for one command, or set LAB_DRIVER to choose a default driver for the current shell.

Orchestrators

Orchestrator adapters define what gets installed, verified, authenticated, and started inside a lab.

TypeDescriptionSupported AgentsDetails
claude-codeAnthropic Claude Code CLIClaude CodeClaude Code
codexOpenAI Codex CLICodexCodex
gastownGas Town HQ and workspace shellClaude CodeGas Town

Inspect what an adapter provides for a given type:

taxiway describe <type>

Typical flow:

  1. Choose an adapter type.
  2. Run taxiway up <lab> --type <type>, optionally with --repo <url>.
  3. Complete adapter authentication when required.
  4. Attach to the lab with taxiway shell <lab>.
  5. Run the workflow in the attached shell or orchestrator session.

How-to

Contributing