ProjectMind

Your project, explained by AI.

by Plaintext · MPL-2.0

ProjectMind uses AI-ready project maps to explain software architecture, classes, modules and relationships in a way humans and coding agents can navigate. It's a lightweight, **read-only** architecture browser for source code that pairs bidirectionally with LLM-driven coding agents — Claude Code, ChatGPT / OpenAI Codex, Gemini CLI, Cursor, and any other frontier model that speaks the **Model Context Protocol (MCP)**.

An AI agent authors this tour live over MCP — steps, line highlights and narration are pushed into the viewer. No human clicked anything.

**Status:** v0.12 — MCP server + desktop app for **macOS, Linux and Windows**, with signed auto-updates. Java + Rust language plugins, Spring + Lombok framework recognisers, sixteen diagram types (see the catalogue below — from bean graph and C4 container up to an animated live bean graph and a 3D code city), an editable C4 model with draw.io export and in-app editing, Markdown + HTML browsers (sandboxed), the Code↔Doc bridge (repo docs and Confluence / Jira / issue references per class), guided AI walkthroughs with quiz support, presenter mode with PDF tour export, an Architect's Cockpit (risk atlas, pattern-drift detection, semantic tour lookup, morning briefing), live AI-generated HTML/Markdown artifacts, and bidirectional MCP sync between LLM, desktop app and browser.

Quickstart

Install the desktop app + MCP server with one line. The script picks the right pre-built bundle for your OS / arch, no build toolch