# gastownhall/gascity

Orchestration-builder SDK for multi-agent coding workflows

Repository: https://github.com/gastownhall/gascity
Canonical: https://ross.abutalabs.com/products/gascity
Language: Go
License: MIT
License Family: permissive
Last push: 2026-09-03T02:00:21+00:00

## Health v2 (maintenance only)
Score: 82/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 100, release rhythm 98, longevity 13
- inputs: {"age_days": 193, "days_push": 0, "days_rel": 18, "gap_med": 3.0, "n_releases_24m": 21}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1217, forks 390 (observed 2026-09-03T02:15:12.221504+00:00)

## What it is
Gas City is an orchestration-builder SDK in Go for composing multi-agent coding workflows, extracted from the Gas Town project. It provides declarative configuration, runtime providers (tmux, subprocess, Kubernetes, ACP), work routing, and a controller loop that reconciles desired agent state.

## Use cases
- orchestrate multiple AI coding agents across projects
- route work items to available coding agents automatically
- run agent fleets under a supervisor that reconciles desired state
- manage multi-project agent setups with scoped orchestration
- configure agent runtimes declaratively in a toml file

## When to choose
- you need reusable infrastructure for coordinating many coding agents
- you want declarative, reconciled multi-agent orchestration rather than ad-hoc scripts
- you need pluggable runtimes like tmux, subprocess, or Kubernetes

## When to avoid
- you need a simple single-agent coding assistant
- you want a GUI-based agent orchestration tool
- your workflows are unrelated to coding agents

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, workflow-automation, scheduling, developer-tools, cli
- domain: developer-tools
- platform: go, cli
- tags: multi-agent-orchestration, coding-agents, declarative-configuration, tmux, work-routing, reconciliation-loop, ai-agents, automation, command-line, linux, macos

## Member repositories
- gastownhall/gascity (main) score 82

## Provenance
- Observed fields: from GitHub, fetched 2026-09-03T02:15:12.221504+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:25:34.585178+00:00, confidence not recorded.
  - readme: https://github.com/gastownhall/gascity (fetched 2026-09-03T02:15:12.221504+00:00, sha 86b3a209ac5b)
- Data as of 2026-08-30T08:39:29.467469+00:00.