I built a tool that gives Claude Code permanent memory of your codebase

ProductMechanics — Tue, 02 Jun 2026 09:52:21 +0000

The problem

Every time I started a session with Claude Code
I had to re-explain my entire project.

What framework I use. How my folders are
structured. What naming conventions I follow.
What decisions I have already made.

Every. Single. Session.

It was slowing me down and I knew there had
to be a better way.

What I built

I built stackbrief. One command scans your
repo and opens a local visual dashboard
showing your full codebase intelligence.

npx stackbrief scan

It opens a dashboard at localhost:3000 showing:

Interactive code map of your architecture
Dependency version comparison against npm
Convention detection (naming, async patterns, error handling)
Context health score
MCP server so Claude Code pulls context automatically

How it works

stackbrief reads every file in your project
and builds a structured understanding of it.
It detects your framework, architecture
pattern, modules, dependencies, and coding
conventions.

It then writes a CLAUDE.md file to your
project and starts an MCP server on port 3001.
Claude Code picks this up automatically before
every session. No more explaining your project
from scratch.

AI chat that actually knows your code

The dashboard has an Ask your codebase
section. Unlike generic AI chat, this
assistant has read every file in your project.
Ask it about your own architecture and get
answers specific to your code.

Works with Ollama (free, fully local),
Claude, OpenAI, or any OpenAI-compatible
provider including Groq, Mistral, and
local runners like LM Studio and AnythingLLM.

Zero config, fully local

No cloud. No telemetry. No account required.
Everything runs on your machine.

npx stackbrief scan

That is it. The dashboard opens automatically.

Try it

GitHub: https://github.com/ragavtech/stackbrief

Built with Node.js and TypeScript.
Open source, MIT license.

Would love to hear what you think.