Documentation
The full reference for Closedloop.ai — the spec-driven, AI-first delivery platform that closes the loop on your SDLC.
Welcome to the Closedloop.ai documentation hub.
Closedloop.ai is a platform for team-based agentic software development. It combines a browser-based control plane, a desktop execution client, and a suite of Claude Code plugins into a single system that turns scoped intent into shipped code through repeatable, artifact-bound loops.
This documentation is organized so both humans and AI agents can use it as ground truth:
- Getting Started — the fastest path from install to a first completed loop.
- Guides — the Dashboard, Sessions, and Branches screens.
- Reference — the Sessions screen and the Desktop gateway.
- Workflows — how-to guides for bootstrapping a repo, planning, code review, and sharing learnings.
- MCP Server — the tools AI agents use to work with Closedloop over the Model Context Protocol.
- Resources — troubleshooting, templates, and a comparison with chat-based workflows.
- API Reference — the REST API: authentication, errors, pagination, and endpoints for documents, comment threads, artifact links, projects, tags, users, search, and agent sessions.
Start here
What ships with Closedloop.ai
| Surface | What it does |
|---|---|
| Web app (control plane) | Defines work, stores artifacts, coordinates teams, renders activity. |
| Desktop app | Electron app that exposes a localhost HTTP gateway. |
| Claude Code plugins | The plugins the installer adds — code, code-review, platform, self-learning — that ship the multi-agent orchestration used by loops. |