Install AI Architect (Bito-hosted)

Deploy AI Architect on Bito's managed infrastructure for instant setup and effortless maintenance.

This guide walks you through setting up Bito-hosted AI Architect. You'll connect your Git account (GitHub, GitLab, or Bitbucket) to index your repositories, then use the MCP server credentials to integrate AI Architect with your coding agents. This enables your agents to access codebase-aware context and provide more accurate, relevant answers.

Bito-hosted vs. Self-hosted AI Architect

Bito offers two deployment options for AI Architect:

  1. Bito-hosted (Fully managed by Bito β€” no infrastructure setup required)

  2. Self-hosted (Run AI Architect on your own infrastructure for maximum control)

Bito-hosted
Self-hosted

Infrastructure

Bito manages indexes and infrastructure on our secure servers

You host AI Architect in your own environment

Code storage

We don't store your code after indexing β€” only repository metadata is retained. Code is fetched at runtime as needed.

Full control over your data and indexes

Maintenance

Fully managed by Bito

Requires infrastructure setup and maintenance

For information on self-hosted deployment, visit the self-hosted installation guide.

Installation steps

1

Connect your Git provider

Log in to Bito Cloudarrow-up-right and select a workspace to get started.

Use the Bito UI to connect your Git provider account (GitHub, GitLab, or Bitbucket). This enables Bito to clone your repositories and fetch code at runtime when needed.

2

Submit repositories for indexing

Contact the Bito team at [email protected]envelope with a list of repositories you want to index. Include the repository names and paths.

3

Bito creates your indexes

Bito will:

  • Clone your repositories

  • Create optimized indexes for semantic search

  • Remove the cloned code from our servers (only index data is retained)

4

Receive your MCP connection details

Once your indexes are ready, Bito will provide you with:

  • Bito MCP URL

  • Bito MCP Access Token

Use these credentials to connect AI Architect to your AI coding agents (Cursor, Claude Code, Windsurf, GitHub Copilot, etc.).

Once connected, AI Architect provides codebase-aware context to your coding agent, enabling more accurate answers.

Code retrieval at runtime

Bito-hosted AI Architect includes smart code retrieval (getCode MCP tool) that works behind the scenes. When you ask questions about specific code β€” like "show me the authenticate method in the Auth class" β€” AI Architect automatically fetches the relevant code at runtime using your Git credentials.

This means you get detailed, accurate code references without storing any code on Bito's servers. Code is fetched on-demand and never persisted.

Need help?

If you have questions about the setup process or need to modify your indexed repositories, reach out to the Bito team at [email protected]envelope. We're here to help you get the most out of AI Architect.

Last updated