Cinatra Documentation
Cinatra is the open source AI workspace for teams, built on open AI standards — a workspace where people, AI assistants, and autonomous agents work together on durable workflows.
New here?
Section titled “New here?”Run your first agent with the Quickstart, or read Why Cinatra for what the platform unlocks.
- User — running agents, chat, human-in-the-loop (HITL) review, dashboards, skills, cross-instance collaboration
- Admin — the
/configuration/*area: marketplace, extensions, permissions, providers, telemetry, instance settings - Developer — authoring agents and extensions, the contributor workflow (planned with GSD — “Git. Ship. Done”, the open-gsd spec-driven development framework), and the day-to-day developer loop
- Hosting — installation, configuration, troubleshooting; what an operator needs to know
- Platform — architecture, subsystem contracts, the objects layer, security, connectors, artifacts, workflows, open standards, and CI policy
- MCP — the Model Context Protocol server (external + internal), authentication, primitives, and clients
- Design — the Cinatra design system: the normative spec, the design skill, and the operational rulebook
- Glossary — canonical concepts and terminology
- Why Cinatra — what the platform unlocks
- Comparisons — Cinatra vs ChatGPT Workspace Agents, Claude Cowork, Vercel Open Agents, Managed Agents, Amazon Quick, and Runwork
License
Section titled “License”The documentation content in this repository is licensed under CC-BY-4.0. Code snippets embedded in the documentation are licensed under Apache-2.0, matching the Cinatra code repository.
Docs content licensed under CC-BY-4.0; embedded code snippets under Apache-2.0.