For the complete documentation index, see llms.txt. This page is also available as Markdown.

Overview

Run AI Architect entirely inside your own infrastructure. Your source code, indexed knowledge graph, and credentials never leave your environment.

Prefer zero infrastructure? Bito-hosted AI Architect runs in Bito's cloud with a 3-step setup. Self-hosted is designed for teams that must keep code and data within their own network.

Choose your deployment mode

Choose based on who uses it and where it runs.

Standalone
Enterprise

Designed for

One person, evaluation or personal use

A team sharing one deployment

Runs on

Your workstation

A shared server or cluster

Infrastructure

Docker only

Docker Compose or Kubernetes

Knowledge graph

Local to your machine

Shared across the team

MCP access

https://localhost:5001

Your host or domain, behind a proxy or ingress

AI coding agent setup

Registered automatically

Configured per user

Authentication

Bearer token

Bearer, Bito Auth, or Enterprise IdP

Installation

One command (curl | bash)

One command (curl | bash)

Setup time

5 to 10 minutes

15 to 30 minutes

Not sure? Start with Standalone to evaluate on your workstation, then move to Enterprise when you are ready to share it with your team. Both modes run the same platform. Note that switching modes re-indexes your repositories from scratch, so keep the repository count small while evaluating.

Plans: Teams of up to five members can use self-hosted AI Architect for free with their own LLM API keys. Larger teams require the Bito Enterprise Plan, which includes bundled LLM tokens. Powering the Bito AI Code Review Agent with AI Architect also requires the Enterprise Plan, regardless of team size. Contact support@bito.ai to get started.

How it works

Both modes index your repositories into a knowledge graph and serve it over an MCP endpoint that your AI coding agents (Claude Code, Cursor, Windsurf, VS Code, JetBrains) query for cross-repository context. AI Architect reaches out only to Bito for licensing and to your LLM provider for inference.

Get started

Before you begin, review Prerequisites & requirements for the accounts, tokens, hardware, and network access you will need.

Last updated