Documentation
Upstream OpenGantry guides for adoption, architectural boundaries, agent orchestration graphs, and development — fetched at build time from the CLI repo.
Get started
Install, run your first mission, and wire the CLI into your IDE agents and CI.
- Adoption Git-native org floor, ledger, and cross-repo gates. The spoke still enforces; nothing here requires a hub.
- Kata ~15 minutes to complete your first scoped mission graph. Every step has a headless variant for CI and IDE agents.
- Integrations OpenGantry is tool-agnostic and vendor-neutral — any agent that can run shell commands can participate in the GXT graph.
- CI / CD Diagnostics (gantry verify: chatter) go to stderr. The document is the only stdout payload. Redirect stdout only.
- Architectural boundaries OpenGantry is a domain-agnostic governance layer for autonomous agents.
- Agent graph OpenGantry is the CLI contract + verify envelope for external autonomous agents (e.g. Hermes).
Concepts
Why the mission/verify graph exists and how it maps to audit and compliance work.
- Manifesto The current trajectory of AI-assisted software engineering has a fatal flaw.
- Use cases Product pitch and problem framing: README.
- Core capabilities This page explains why OpenGantry's capabilities exist and when to use them.
- Compliance How OpenGantry's GXT workflow maps to common audit questions for teams using AI-assisted development — especially in regulated domains (fintech, health…
Contributing
Working on OpenGantry itself — the repo dogfoods the same substrate it ships.
Reference
Release history and architecture decision records.