Launched this week

Archaic AI

Launched this week

A living architecture map — for you and your AI agent

6 followers

A living architecture map — for you and your AI agent

6 followers

Visit website

Archaic analyzes your codebase with AI and generates an interactive architecture map: services, connections, execution flows, and deep dives. But it's not just for you. Your AI agent can read it, reason about it, and update it as it works. The desktop app is local-first with your own LLM keys (Claude, GPT-4, Gemini, Ollama). An MCP server connects to Claude Code so your agent always knows how the system is structured. Create a task in Desktop, Claude implements it, and the diagram updates live.

Interactive

Free

Launch tags:Productivity•Software Engineering•Developer Tools

Launch Team / Built With

Synter MCP for Claude & Cursor — The most performant Ads MCP available to use with Your AI

The most performant Ads MCP available to use with Your AI

Promoted

Maker

📌

Hey PH! I built Archaic because vibe coding has a problem: the more your AI agent builds, the less you understand what it actually built. You can read the code, but you lose the big picture — what connects to what, how data flows, and where the boundaries are. And when you try to explain the architecture to your agent in plain text, things get lost. It's hard to describe a system precisely enough for an agent to reason about it well. Archaic solves both sides. It generates an interactive architecture map from your codebase — a visual, structured representation that both you and your agent can work with. The desktop app is local-first (bring your own LLM keys, code stays on your machine). An MCP server connects the map to Claude Code, so your agent can read the architecture, pick up tasks you create in the UI, implement changes, and update the diagram as it goes. The loop I'm most excited about: create a task like "add Bedrock as an LLM provider" in the desktop UI, Claude picks it up, implements it, and the architecture map updates live with the new component. Would love to hear — how do you keep track of your architecture as your agent builds?

Report

3d ago

Forum Threads

p/archaic-ai

•

1d ago

How do you keep track of what your AI agent actually built?

We've been vibe coding more than ever Cursor, Claude Code, Copilot agents spinning up entire features. But I keep running into the same issue: after a few sessions, I have no idea how the pieces actually fit together. The code works, but I couldn't draw the architecture on a whiteboard if someone asked me to. Curious how others deal with this. Do you just read through the code? Maintain docs manually? Or have you given up and just trust the agent knows what it's doing?

View all